Browse

ftp://ftp.cis.ohio-state.edu (1228)

	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pollack.perceptrons.ps, 19890823 Book Review No Harm Intended Marvin L. Minsky and Seymour A. Papert. Perceptrons: An Introduction to Computational Geometry, Expanded Edition. Cambridge, MA: MIT Press, 1988. 292pp. Reviewed by Jordan B. Pollack The Authors are professors at the Massachusetts Institute of Technology, Minsky in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pollack.nips88.ps.Z, 19890823 IMPLICATIONS OF RECURSIVE DISTRIBUTED REPRESENTATIONS Jordan B. Pollack Laboratory for AI Research Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pollack.newraam.ps.Z, 19890915 Recursive Distributed Representations Jordan B. Pollack Laboratory for AI Research & Computer & Information Science Department The Ohio State University 2036 Neil Avenue Columbus, OH 43210 (614) 292-4890 pollack@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/barto.control.ps.Z, 19890915 Connectionist Learning for Control: An Overviewy Andrew G. Barto Department of Computer and Information Science University of Massachusetts, Amherst MA 01003 COINS Technical Report 89-89 September 1989
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/barto.sequential_decisions.ps.Z, 19890915 Learning and Sequential Decision Makingy Andrew G. Barto Department of Computer and Information Science University of Massachusetts, Amherst MA 01003 R. S. Sutton GTE Laboratories Incorporated Waltham, MA 02254 C. J. C. H. Watkins Philips Research Laboratories Cross Oak Lane, Redhill Surrey RH1 5HA,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tenorio.speech_dev.ps.Z, 19891005 Adaptive Networks as a Model for Human Speech Development M. Fernando Tenorio M. Daniel Tom School of Electrical Engineering and Richard G. Schwartz Department of Audiology and Speech Sciences Parallel Distributed Structures Laboratory Purdue University West Lafayette, IN 47907 August 1989 TR-EE 89-54
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gasser.phonology.ps.Z, 19900101 1 Networks that Learn Phonology Michael Gasser Chan-Do Lee Computer Science Department, Indiana University Bloomington, IN 47405, USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/honavar.develop-learn.ps.Z, 19900212 Perceptual Development and Learning: From Behavioral, Neurophysiological, and Morphological Evidence To Computational Models delim $$ Vasant Honavar Computer Sciences Department University of Wisconsin-Madison
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/honavar.control.ps.Z, 19900212 Coordination and Control Structures and Processes: Possibilities for Connectionist Networks (CN) Vasant Honavar & Leonard Uhr Computer Sciences Department University of Wisconsin-Madison
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.contincomp.ps.Z, 19900227 o i o s o a io : a i assi e arallelis erio sl 1 B. J. MacLennan Department of Computer Science University of Tennessee Knoxville, TN 37996-1301 mclennan utkcs2.cs.utk.edu 1 Discrete vs. Continuous Computation Modern computation is rooted in the discrete. This is most obvious in the digital (especially
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.fieldcomp.ps.Z, 19900228 1 n en s ield om ut tion 3 1 Introduction 3 1.1 Truly Massive Parallelism : : : : : : : : : : : : : : : : : : : : : : : : 3 1.2 Field Transformation : : : : : : : : : : : : : : : : : : : : : : : : : : : 4 1.3 Classes of Field Transformations : : : : : : : : : : : : : : : : : : : : : 4 1.4 General
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/witbrock.gf11.ps.Z, 19900316 An Implementation of Back-Propagation Learning on GF11, a Large SIMD Parallel Computer Michael Witbrock and Marco Zagha December 1989 CMU-CS-89-208 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/frean.upstart.ps.Z, 19900327 Edinburgh Physics Department Preprint # 89/469 The Upstart Algorithm : a method for constructing and training feed-forward neural networks Marcus Frean Department of Physics and Centre for Cognitive Science Edinburgh University, The Kings Buildings Mayfield Road, Edinburgh, Scotland email :
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jagota.hsn.ps.Z, 19900327 A new Hopfield-style network for content-addressable memories Arun Jagota (jagota@cs.buffalo.edu) Technical Report 90-02, March 1990 Dept Of Computer Science, State University Of New York Buffalo, NY 14260
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jacobs.modular.ps.Z, 19900328 Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks. Robert A. Jacobs1 Michael I. Jordan2 Andrew G. Barto1 1Department of Computer & Information Science University of Massachusetts, Amherst, MA 01003 2Department of Brain & Cognitive Sciences
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yu.epsilon.ps.Z, 19900410 Descending Epsilon in Back-Propagation: A Technique for Better Generalization1 Yeong-Ho Yu Robert F. Simmons Department of Computer Sciences and Artificial Intelligence Laboratory Taylor Hall 2.124, University of Texas at Austin, Austin, Texas 78712-1188 March 1990 AI90-130
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yu.output-biased.ps.Z, 19900410 Extra Output Biased Learning1 Yeong-Ho Yu Robert F. Simmons Department of Computer Sciences and Artificial Intelligence Laboratory Taylor Hall 2.124, University of Texas at Austin, Austin, Texas 78712-1188 March 1990 AI90-128
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.fig6.ps.Z, 19900423 KOLEN & POLLACK Figure 26 Figure 29 Figure 30 Figure 27 Figure 28 W Weight 1 -0.34959000 -0.34959000 -0.3495900 eight 2 0.00560000 0.00560000 0.00560000 5 W Weight 3 -0.26338813 0.39881098 0.6506070 eight 4 0.75501968 -0.16718577 0.75501968 1 W Weight 5 0.47040862 -0.28598450 0.9128171 eight 6
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.fig5.ps.Z, 19900423 KOLEN & POLLACK Figure 26 : h=(0.0,4.0) a=(0.0,1.25) KOLEN & POLLACK Figure 27 : h=(0.0,4.0) a=(0.0,1.25) KOLEN & POLLACK Figure 28 : h=(0.0,4.0) a=(0.0,1.25) KOLEN & POLLACK Figure 29 : h=(3.456,3.504) a=(0.835,0.840) KOLEN & POLLACK Figure 30 : h=(3.84,3.936) a=(0.59,0.62)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.fig3.ps.Z, 19900423 KOLEN & POLLACK Figure 14 : (-20.00000, -20.00000) step .200000 Figure 15 : Solution Networks Figure 16 : (-4.500000, -4.500000) step .030000 Figure 17 : Solution Networks Figure 18 : (-1.680000, -1.350000) step .002400 Figure 19 : Solution Networks
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.fig4.ps.Z, 19900423 KOLEN & POLLACK Figure 20 : (-1.536000, -1.197000) step .000780 Figure 21 : Solution Networks Figure 22 : (-1.472820, -1.145520) step .000070 Figure 23 : Solution Networks Figure 24 : (-1.467150, -1.140760) step .000016 Figure 25 : Solution Networks
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.fig2.ps.Z, 19900423 KOLEN & POLLACK Figure 8 : (-6-4XY-6-6+9-4-9) h=3.00 a=0.50 Figure 9 : (-2+1+9-1X-3+8Y-4) h=2.75 a=0.20 Figure 10 : (+1+8-3-6X-1+1+8Y) h=3.50 a=0.90 Figure 11 : (+7+4-9-9-5Y-3+9X) h=3.00 a=0.70 Figure 12 : (-9.0,-1.8) step .018 Figure 13 : (-6.966,-0.500) step .004
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stolcke.tr90-15.ps.Z, 19900425 INTERNATIONAL COMPUTER SCIENCE INSTITUTE I 1947 Center Street ffl Suite 600 ffl Berkeley, California 94704 ffl 1-415-642-4274 ffl FAX 1-415-643-7684 Learning Feature-based Semantics with Simple Recurrent Networks Andreas Stolcke1 TR-90-015 April 1990
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gasser.morpho.ps.Z, 19900425 1 Networks and Morphophonemic Rules Revisited Michael Gasser Chan-Do Lee Computer Science Department Indiana University Bloomington, IN 47405
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/feldman.tr90-9.ps.Z, 19900425 INTERNATIONAL COMPUTER SCIENCE INSTITUTE I 1947 Center Street ffl Suite 600 ffl Berkeley, California 94704 ffl 1-415-642-4274 ffl FAX 1-415-643-7684 Miniature Language Acquisition: A touchstone for cognitive science Jerome A. Feldman, George Lakoff, Andreas Stolcke and Susan Hollbach Weber TR-90-009
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.fig0.ps.Z, 19900427 L=1.0 M=0.0 L=1.0 M=0.5 L=1.0 M=0.9 L=2.0 M=0.0 L=2.0 M=0.5 L=2.0 M=0.9 Non Convergence After 50,000 Trials r 0.00 10.00 20.00 30.00 40.00 50.00 60.00 70.00 80.00 90.00 0.00 2.00 4.00 6.00 8.00 10.00 Figure 1: Percentage T-Convergence vs. Initial Weight Range
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.tr.ps.Z, 19900427 Back Propagation is Sensitive to Initial Conditions John F. Kolen Jordan B. Pollack Laboratory for Artificial Intelligence Research Computer and Information Science Department The Ohio State University Columbus, Ohio 43210, USA kolen-j@cis.ohio-state.edu, pollack@cis.ohio-state.edu TR 90-JK-BPSIC
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mel.sigmapi3.ps.Z, 19900502 The Sigma-Pi Column: A Model of Associative Learning in Cerebral Neocortex Bartlett W. Mel Computation and Neural Systems Program, 216-76 California Institute of Technology Pasadena, California 91125 (818)356-3643, mel@aurel.caltech.edu April 30, 1990 CNS Memo 6
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mel.sigmapi2.ps.Z, 19900502 Figure 8: Evidence for an unconditioned eacher" input pathway with priveledged access to modules of cortical pyramidal cells. One class of small spiny cells which receive thalamocortical input send their axons vertically to enclose, as if in a sleeve, the clumped apical dendrites of a group of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mel.sigmapi1.ps.Z, 19900502 Shepherd, G.M., Brayton, R.K., Miller, J.P., Segev, I., Rinzel, J., & Rall, W. Signal enhancement in distal cortical dendrites by means of interactions between active dendritic spines. PNAS, 1985, 82, 2192-2195. Shepherd, G.M., Woolf, T.B., & Carnevale, N.T. Comparisons between active
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stjohn.story.ps.Z, 19900618 The Story Gestalt St. John 18 To sum up, cue-based constraint satisfaction provides a new approach to story comprehension. Some of the difficulties found in other models of story comprehension are ameliorated by the qualities of this approach. There is much to story comprehension that the model does not
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sontag.capabilities.ps.Z, 19900627 ON THE RECOGNITION CAPABILITIES OF FEEDFORWARD NETS Eduardo D. Sontag SYCON - Rutgers Center for Systems and Control Department of Mathematics Rutgers University, New Brunswick, NJ 08903 Phone: (201)932-3072 E-mail: sontag@hilbert.rutgers.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ahmad.tr90-11.ps.Z, 19900717 INTERNATIONAL COMPUTER SCIENCE INSTITUTE 1947 Center Street Suite 600 Berkeley, California 94704 (415) 643-4274 FAX (415) 643-7684 A Network for Extracting the Locations of Point Clusters Using Selective Attention1 Technical Report #90-011 July 16, 1990
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mani.function-space.ps.Z, 19900730 Learning by Gradient Descent in Function Space Ganesh Mani Computer Sciences Department University of Wisconsin\|Madison Madison, WI 53706. ganesh@cs.wisc.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.pdplearn.ps.Z, 19900807 Learning in Parallel Distributed Processing Networks: Computational Complexity and Information Content1 JOHN F. KOLEN2 ASHOK K. GOEL3 August 7, 1990 To appear in IEEE Systems, Man, and Cybernetics. Keywords: Back propagation, computational complexity, information content, learning, neural networks,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plunkett.tr9020.ps.Z, 19900913 From Rote Learning to System Building Kim Plunkett Virginia Marchman CRL Technical Report 9020 September 1990 Center for Research in Language University of California, San Diego La Jolla, CA 92093-0126 From Rote Learning to System Building: Acquiring Verb Morphology in Children and Connectionist Nets
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dietterich.comparison.ps.Z, 19900913 A Comparison of ID3 and Backpropagation for English Text-to-Speech Mapping Thomas G. Dietterich tgd@cs.orst.edu Hermann Hild s hild@irav1.ira.uka.de Ghulum Bakiri haya@cs.orst.edu Department of Computer Science Oregon State University Corvallis, OR 97331-3102
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pollack.neuring.ps.Z, 19900919 hhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh Chapter 4 Limits of Connectionism hhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh 4.1. Introduction Let us distinguish two parts of a programming language. First, its framework, which gives the overall rules of the system, and second, its changable parts, whose existence is
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hampshire.bayes90.ps.Z, 19900923 Equivalence Proofs for Multi-Layer Perceptron Classifiers and the Bayesian Discriminant Function John B. Hampshire II Dept. of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh, PA 15213-3890 Barak A. Pearlmuttery School of Computer Science Carnegie Mellon University Pittsburgh,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cliff.manifesto.ps.Z, 19901029 Computational Neuroethology: A Provisional Manifesto D. T. Cliff May 1990 Cognitive Science Research Paper Serial No. CSRP 162 The University of Sussex School of Cognitive and Computing Sciences Falmer Brighton BN1 9QN England, U.K. ntro uction This paper is concerned with approaches to computational
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/baird.oscmem.ps.Z, 19901109 Learning with Synaptic Nonlinearities in a Coupled Oscillator Model of Olfactory Cortex Bill Baird Depts. Mathematics and Molecular and Cell Biology, U.C.Berkeley, Berkeley, Ca. 94720
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fahlman.quickprop-tr.ps.Z, 19901120 An Empirical Study of Learning Speed in Back-Propagation Networks Scott E. Fahlman September 1988 CMU-CS-88-162
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tsirukis.optimize.ps.Z, 19901120 This page is intentionally left blank. COMPUTATIONAL PROPERTIES OF GENERALIZED HOPFIELD NETWORKS APPLIED TO NONLINEAR OPTIMIZATION Athanasios G. Tsirukis and Gintaras V. Reklaitis School of Chemical Engineering Manoel F. Tenorio School of Electrical Engineering Technical Report TREE 89-69 School of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bengio.learn.ps.Z, 19901121 c ill ni ersit , chool of omputer cience, ni ersit street, ontreal, c, ana a, ni ersite e ontreal, epartement nformati ue et e echerche perationelle, . . , succursale , ontreal, c, ana a, 1 ntro uction One of the major goals of both biological neural networks modeling and artificial neural networks
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/chalmers.evolution.ps.Z, 19901125 The Evolution of Learning: An Experiment in Genetic Connectionism David J. Chalmers Center for Research on Concepts and Cognition Indiana University Bloomington, Indiana 47408. E-mail: dave@cogsci.indiana.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/moller.conjugate-gradient.ps.Z, 19901203 PB-339 PREPRINT A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning Martin F. M ller November 13, 1990 Computer Science Department University of Aarhus Denmark This is a preprint of a paper intended for publication in a journal. Since changes may be made before publication, this preprint
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kruschke.gain.ps.Z, 19901206 Kruschke & Movellan Benefits of Gain, p. 19 D. Psaltis & M. Neifeld The emergence of generalization in networks with constrained representations." In: Proceedings of the IEEE International Conference on Neural Networks, San Diego CA, 24-27 July 1988. Piscataway NJ: IEEE Service Center, v.I,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jagota.wordrec.ps.Z, 19901213 Degraded Printed Word Recognition with a Hopfield-style Network Arun Jagota (jagota@cs.buffalo.edu) Dept Of Computer Science State University Of New York Buffalo
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pearlmutter.dynets.ps.Z, 19901213 Dynamic Recurrent Neural Networks Barak A. Pearlmutter December 1990 CMU-CS-90-196 (supersedes CMU-CS-88-191) School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jagota.tr90-25.ps.Z, 19901213 The Hopfield-style Network as a Maximal-Clique Graph Machine Arun Jagota (jagota@cs.buffalo.edu) Technical Report 90-25, September 1990 Dept Of Computer Science, State University Of New York At Buffalo
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/honavar.symbolic.ps.Z, 19901218 Symbol Processing Systems, Connectionist Networks, and Generalized Connectionist Networks Vasant Honavar Department of Computer Science Iowa State University Leonard Uhr Computer Sciences Department University of Wisconsin-Madison Technical Report #90-23, December 1990 Department of Computer Science
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/NIPS90/pratt.dtnn.handout.ps.Z, 19901226 Neural Networks and Decision Tree Induction: Exploring the relationship between two research areas A NIPS '90 workshop, 11/30/1990, Keystone, Colorado Workshop Handout/bibliography Workshop co-chairs: L. Y. Pratt S. W. Nortony The fields of Neural Networks and Machine Learning have evolved separately in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/NIPS90/pratt.dtnn.ps.Z, 19901226 Summary of the NIPS '90 workshop on comparing Decision Trees and Neural Networks Lorien Y. Pratt This document describes a workshop on comparing decision trees and neural networks which was held in conjunction with NIPS '90 on November 30, 1990 in Keystone, Colorado. The workshop handout is also
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lakoff.war.ps.Z, 19910102 T Metaphor and War he Metaphor System Used to Justify War in the Gulf L George Lakoff inguistics Department yUniversity of California at Berkele (lakoff@cogsci.berkeley.edu) n t Metaphors can kill. The discourse over whether we should go to war i he gulf is a panorama of metaphor. Secretary of State
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sontag.twolayer.ps.Z, 19910107 Report SYCON-90-11 FEEDBACK STABILIZATION USING TWO-HIDDEN-LAYER NETS Eduardo D. Sontag Department of Mathematics, Rutgers University, New Brunswick, NJ 08903 (908) 932-3072, E-mail: sontag@hilbert.rutgers.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/NIPS90/niebur.NIPS-ws1.ps, 19910108 Summary of workshop #1 Oscillations in Cortical Systems" Ernst Niebur January 7, 1991 Computation and Neural Systems Program, California Institute of Technology Pasadena CA 91125, USA ernst@descartes.cns.caltech.edu It has generally been assumed that oscillations in the 30 { 80 Hz range play a
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/NIPS90/fahlman.wkshop.ps.Z, 19910111 Summary of NIPS-90 Workshop: Constructive and Destructive Learning Algorithms Workshop Leader: Scott E. Fahlman School of Computer Science Carnegie-Mellon University Pittsburgh, PA 15213 Phone: (412) 268-2575 Internet: scott.fahlman@cs.cmu.edu This was a two-day workshop on Nov. 30 and Dec. 1, 1990,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/honavar.generate.ps.Z, 19910115 Generative Learning Structures and Processes for Generalized Connectionist Networks Vasant Honavar Department of Computer Science Iowa State University Leonard Uhr Computer Sciences Department University of Wisconsin-Madison Technical Report #91-02, January 1991 Department of Computer Science Iowa State
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.integrate.ps.Z, 19910115 Integrating Rules and Connectionism for Robust Reasoning Ron Sun Brandeis University Computer Science Department Waltham, MA 02254 (617) 736-2712 rsun@cs.brandeis.edu Technical Report TR-CS-90-154 January 10, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sontag.nips90.ps.Z, 19910115 FEEDFORWARD NETS FOR INTERPOLATION AND CLASSIFICATION Eduardo D. Sontag SYCON - Center for Systems and Control Department of Mathematics Rutgers University, New Brunswick, NJ 08903 (908)932-3072; E-mail: sontag@hilbert.rutgers.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sanger.trees.ps.Z, 19910117 Basis-Function Trees as a Generalization of Local Variable Selection Methods for Function Approximation Terence D. Sanger Dept. Electrical Engineering and Computer Science Massachusetts Institute of Technology, E25-534 Cambridge, MA 02139
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/krogh.generalization.ps.Z, 19910121 Dynamics of Generalization in Linear Perceptrons Anders Krogh Niels Bohr Institute Blegdamsvej 17 DK-2100 Copenhagen, Denmark John A. Hertz NORDITA Blegdamsvej 17 DK-2100 Copenhagen, Denmark
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/horiuchi.motion.ps.Z, 19910121 A Delay-Line Based Motion Detection Chip Tim Horiuchiy John Lazzaro Andrew Moorey Christof Kochy yComputation and Neural Systems Program Department of Computer Science California Institute of Technology MS 216-76 Pasadena, CA 91125
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.csa.ps.Z, 19910123 Continuous Spatial Automata B. J. MacLennan Department of Computer Science University of Tennessee Knoxville, TN 37996-1301 maclennan@cs.utk.edu CS-90-121 November 26, 1990
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rowat.learn-osc.ps.Z, 19910123 Learning algorithms for oscillatory networks with gap junctions and membrane currents Peter F Rowat and Allen I Selverston Biology Department 0322, University of California at San Diego, La Jolla, California 92093-0322, U.S.A Short title: Learning in oscillatory networks To be published in: NETWORK:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tom.hystery.ps.Z, 19910123 The Hystery Unit - A Short Term Memory Model for Computational Neurons M. Daniel Tom M. F. Tenorio Parallel Distributed Structures Laboratory School of Electrical Engineering Purdue University West Lafayette, Indiana 47907, USA December, 1990
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bottou.cooperation.ps.Z, 19910125 A Framework for the Cooperation of Learning Algorithms L on Bottou Patrick Gallinari Laboratoire de Recherche en Informatique Universit de Paris XI 91405 Orsay Cedex France
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/koch.awareness3.ps.Z, 19910129 60:121-130 45. Gray CM, Engel AK, Ko"nig P, Singer W (1990) Stimulus- dependent neuronal oscillations in cat visual cortex I. Receptive field properties and feature dependence. Eur J Neurosci, in press 46. Gray CM, Raether A, Singer W (1989) Stimulus-specific intercolumnar interactions of oscillatory
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/koch.awareness2.ps.Z, 19910129 6 Binding and selective visual attention 6.1 The binding problem There are an almost infinite number of possible, different objects that we are capable of seeing. There cannot be a single neuron, often referred to as a grandmother cell, for each one. The combinatorial possibilities for representing so
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/koch.awareness1.ps.Z, 19910129 CALIFORNIA INSTITUTE OF TECHNOLOGY COMPUTATION AND NEURAL SYSTEMS PROGRAM January 28, 1991 CNS Memo 9 As published in Seminars in The Neurosciences 2: 263{275 (1990). TOWARDS A NEUROBIOLOGICAL THEORY OF CONSCIOUSNESS Francis Cricky and Christof Koch y The Salk Institute 10010 N. Torrey Pines Road, La
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bengio.hybrid_header.ps.Z, 19910219
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bengio.hybrid.ps.Z, 19910219 Intro uction In spite of the fact that speech exhibits features that cannot be represented by a first-order Markov model, Hidden Markov Models (HMMs) of speech units (e.g., phonemes) have been used with a good degree of success in Automatic Speech Recognition (ASR) (e.g., Bahl et al 83; Rabiner &
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.nips90.ps.Z, 19910220 To appear in: Advances in Neural Information Processing Systems 3, Touretzky, D.S., Lippmann, R. (eds.), San Mateo, CA: Morgan Kaufmann Planning with an Adaptive World Model Sebastian B. Thrun German National Research Center for Computer Science (GMD) D-5205 St. Augustin, FRG Knut M oller University of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/holt.finite_error.ps.Z, 19910222 Finite Precision Error Analysis of Neural Network Hardware Implementations Jordan L. Holt, Jenq-Neng Hwang Department of Elect. Engr., FT-10 University of Washington Seattle, WA 98195 1 Introduction The high speed desired in the implementation of many neural network algorithms, such as back-propagation
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yun.quant.ps.Z, 19910227 Analysis of the Effects of Quantization in Multi-Layer Neural Networks Using Statistical Model Yun Xie Department of Electronic Engineering Tsinghua University Beijing 100084, P.R.China Marwan A. Jabri School of Electrical Engineering The University of Sydney N.S.W. 2006, Australia
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jabri.dime.ps.Z, 19910304 Predicting the Number of Vias and Dimensions of Full-custom Circuits Using Neural Networks Techniques Marwan A. Jabri & Xiaoquan Li Systems Engineering and Design Automation Laboratory Sydney University Electrical Engineering NSW 2006 Australia SEDAL Technical Report 1991-1-6
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smieja.minos.ps.Z, 19910305 Multiple Network Systems (Minos) Modules: Task Division and Module Discrimination1 F.J. Smieja German National Research Centre for Computer Science (GMD), Schloss Birlinghoven, 5205 St. Augustin 1, Germany.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yeates.pseudo-kalman.ps.Z, 19910312 A NEURAL NETWORK FOR COMPUTING THE PSEUDO-INVERSE OF A MATRIX AND APPLICATIONS TO KALMAN FILTERING Mathew C. Yeates yCalifornia Institute of Technolog Jet Propulsion Laboratory 9Pasadena, California 9110
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/belew.evol-net.ps.Z, 19910312 Evolving Networks: Using the Genetic Algorithm with Connectionist Learning Richard K. Belew John McInerney Nicol N. Schraudolph Cognitive Computer Science Research Group Computer Science & Engr. Dept. (C-014) Univ. California at San Diego La Jolla, CA 92093 rik@cs.ucsd.edu CSE Technical Report #CS90-174
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yeates.pseudo-kalman-fig.ps.Z, 19910312 Y1Y2Y3X1X2X3SCALING NODE Figure 1 W yy
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kehagias.srn1fig.ps.Z, 19910318 -1 1 2 3 4 5 6 7 8 20 40 60 80 100 120 140 160 180 200 Fig.1 Time U(t) 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 20 40 60 80 100 120 140 160 180 200 Time Fig.2 Y(t) 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 20 40 60 80 100 120 140 160 180 200 Fig.3 Time Y(t)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kehagias.srn2fig.ps.Z, 19910318 -1 1 2 3 4 5 20 40 60 80 100 120 140 160 180 Time Speech Fig.1 phoneme -1 1 2 3 4 5 20 40 60 80 100 120 140 160 180 Fig.2 phoneme Time Speech -1 1 2 3 4 5 20 40 60 80 100 120 140 160 180 Time Speech Fig.3: Actual and Predicted Speech Waveform -1 1 2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kehagias.srn1.ps.Z, 19910318 Stochastic Recurrent Networks Training by the Local Backward-Forward Algorithm Athanasios Kehagias Division of Applied Mathematics Brown University Providence, RI 02912 e-mail: st401843@brownvm.brown.edu March 4, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kehagias.srn2.ps.Z, 19910318 Stochastic Recurrent Networks: Prediction and Classification of Time Series Athanasios Kehagias Division of Applied Mathematics Brown University Providence, RI 02912 e-mail: st401843@brownvm.brown.edu March 4, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/brunak.netgene.ps.Z, 19910318 Prediction of human mRNA donor and acceptor sites from the DNA sequence Soren Brunak, Jacob Engelbrecht and Steen Knudseny Department of Structural Properties of Materials The Technical University of Denmark DK-2800 Lyngby, Denmark y Molecular Biology Computer Research Resource Dana{Farber Cancer
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gasser.same.ps.Z, 19910322 Comparison, Categorization, and Perceptual Dimensions: A Connectionist Model of the Development of the Notion of Sameness Michael Gasser and Linda B. Smith 1 Comparison and Categorization 1.1 Comparison and Cognition The process of comparison is fundamental to behaving organisms. Generalization from
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/french.forgetting.ps.Z, 19910401 CRCC Technical Report 51-1991. Submitted to Cog. Sci. Conf. 1991 Using Semi-Distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks Robert M. French Center for Research on Concepts and Cognition Indiana University 510 North Fess Bloomington, Indiana 47408 e-mail:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pratt.ijcnn91.ps.Z, 19910403 bias toward higher performance for the decomposed network. Whether a decomposed network would learn faster than a non-decomposed network when the number of weights in the two networks is approximately equal remains to be tested. Second, we performed a more extensive search in and ff space than
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pratt.aaai91.ps.Z, 19910403 drafts. Also, Michiel Noordewier and Haym Hirsh provided critical support and encouragement for the research program on which this paper is based. References Barnard, Etienne and Cole, Ronald A. 1989. A neuralnet training program based on conjugate-gradient optimization. Technical Report CSE 89-014,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dietterich.error-correcting.ps.Z, 19910417 Error-Correcting Output Codes: A General Method for Improving Multiclass Inductive Learning Programs Thomas G. Dietterich and Ghulum Bakiri Department of Computer Science Oregon State University Corvallis, OR 97331-3202
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kehagias.hmm89.ps.Z, 19910417 OPTIMAL CONTROL FOR TRAINING: THE MISSING LINK BETWEEN HIDDEN MARKOV MODELS AND CONNECTIONIST NETWORKS Athanasios Kehagias Division of Applied Mathematics Brown University Providence, RI 02912 June 12, 1989
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sankar.ijcnn91_1.ps.Z, 19910423 K. Lang, A. Waibel, and G. Hinton, A Time Delay Neural Network Architecture for Isolated Word Recognition," Neural Networks, vol. 3, no. 1, pp. 233, 1990. A. Rajavelu, M. Musavi, and M. Shirvaikar, A Neural Network Approach to Character Recognition," Neural Networks, vol. 2, no. 5, pp.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sankar.ijcnn91_2.ps.Z, 19910423 5 Summary and Conclusions In this paper, we extended the optimal pruning algorithm for binary classification trees to arbitrary trees such as the NTN. The pruning algorithm was used to improve the generalization of the NTN. We presented simulation results on a speaker independent vowel recognition
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tzirkel.control.ps.Z, 19910501 The first author is supported by grants from Trinity College Cambridge and the Committee of Vice-Chancellors and Principals CUED/F-INFENG/TR.65 Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England March 1991 E. Tzirkel-Hancock & F. Fallside email: et@uk.ac.cam.eng A
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/blank.raam.ps.Z, 19910506 Exploring the Symbolic/Subsymbolic Continuum: A Case Study of RAAM Douglas S. Blank (blank@iuvax.cs.indiana.edu) Lisa A. Meeden (meeden@iuvax.cs.indiana.edu) James B. Marshall (marshall@iuvax.cs.indiana.edu) Department of Computer Science Indiana University Bloomington, Indiana 47405 May 6, 1991 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ring.ml91.ps.Z, 19910508 Incremental Development of Complex Behaviors through Automatic Construction of Sensory-motor Hierarchies (To appear in the proceedings of the Eighth International Workshop on Machine Learning) Mark Ring Department of Computer Sciences University of Texas at Austin, Austin, TX 78712 ring@cs.utexas.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fahlman.rcc.ps.Z, 19910513 The Recurrent Cascade-Correlation Architecture Scott E. Fahlman May 9, 1991 CMU-CS-91-100 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hoehfeld.precision.ps.Z, 19910513 Learning with Limited Numerical Precision Using the Cascade-Correlation Algorithm Markus Hoehfeld and Scott E. Fahlman May 3, 1991 CMU-CS-91-130 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jabri.wpert.ps.Z, 19910515 Weight Perturbation: An Optimal Architecture and Learning Technique for Analog VLSI Feedforward and Recurrent Multi-Layer Networks Marwan Jabri & Barry Flower Systems Engineering and Design Automation Laboratory School of Electrical Engineering University of Sydney
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fritzke.clustering.ps.Z, 19910521 3. Conclusion And Further Research We presented a network model which is able to detect clusters of similar patterns according to an unknown probability distribution. The clustering is done unsupervised guided only by sample vectors according to the distribution. Since our model is a generalization of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cottrell.cogsci91.ps.Z, 19910521 is more frequent than the others, it captures the class. Interestingly, this is not the case if the more frequent item in a synonym class is an arbitrary verb, probably due to the fact that they map similar inputs to very different outputs (see Bartell, Cottrell & Elman, this volume for a thorough
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fritzke.cell_structures.ps.Z, 19910521 To appear in: Proc. of the ICANN-91 Helsinki ( c 1991 by Elsevier Science Publ. B.V.) LET IT GROW { SELF-ORGANIZING FEATURE MAPS WITH PROBLEM DEPENDENT CELL STRUCTURE Bernd FRITZKE Institut f ur Mathematische Maschinen und Datenverarbeitung Lehrstuhl f ur Programmiersprachen Universit at Erlangen-N
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.cogsci91.ps.Z, 19910523 Connectionist Models of Rule-Based Reasoning Ron Sun Brandeis University Computer Science Department Waltham, MA 02254 rsun@cs.brandeis.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/white.comp-hebb.ps.Z, 19910528 To be presented at IJCNN-91 Seattle Competitive Hebbian Learning Ray H. White Departments of Physics and Computer Science University of San Diego San Diego, California 92110 January 21, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plaut.cogsci91.ps.Z, 19910603 Effects of Word Abstractness in a Connectionist Model of Deep Dyslexia David C. Plaut School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 dcp@cs.cmu.edu Tim Shallice Department of Psychology University College London, England WC1E 6BT ucjtsts@ucl.ac.uk To appear in the Proceedings
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mjolsness.grammar.ps.Z, 19910607 Bayesian Inference on Visual Grammars by Neural Nets that Optimize Eric Mjolsness Department of Computer Science Yale University New Haven, CT 06520-2158 May 1, 1990 YALEU-DCS-TR-854
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mackay.bayes-interpolation.1-5.ps.Z, 19910610 Bayesian Interpolation David J.C. MacKay Computation and Neural Systems California Institute of Technology 139{74 Pasadena CA 91125 mackay@hope.caltech.edu May 27, 1991 Submitted to Neural Computation as a review paper
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mackay.bayes-backprop.1-5.ps.Z, 19910610 A Practical Bayesian Framework for Backprop Networks David J.C. MacKay Computation and Neural Systems California Institute of Technology 139{74 Pasadena CA 91125 mackay@hope.caltech.edu May 27, 1991 Submitted to Neural Computation as a long paper
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mackay.bayes-interpolation.11-15.ps.Z, 19910610 W.T. Grandy, Jr., editor (1991). Maximum Entropy and Bayesian Methods, Laramie 1990, Kluwer. S.F. Gull (1988). Bayesian inductive inference and maximum entropy, in Maximum Entropy and Bayesian Methods in science and engineering, vol. 1: Foundations, G.J. Erickson and C.R. Smith, eds., Kluwer.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mackay.bayes-backprop.6-11.ps.Z, 19910610 References Y.S. Abu-Mostafa (1990). The Vapnikhervonenkis dimension: information versus complexity in learning, Neural Computation 1 3, 31217. Y.S. Abu-Mostafa (1990). Learning from hints in neural networks, J. Complexity 6, 19298. J.S. Bridle (1989). Probabilistic interpretation of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mackay.bayes-interpolation.6-10.ps.Z, 19910610 models. Notice as pointed out earlier that this modern Bayesian framework includes no emphasis on defining the `right' prior R with which we ought to interpolate. Rather, we invent as many priors (regularisers) as we want, and allow the data to tell us which prior is most probable. Evaluating the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ahmad.cogsci91.ps.Z, 19910610 1 Efficient Visual Search: A Connectionist Solution Subutai Ahmad and Stephen Omohundro International Computer Science Institute, 1947 Center Street, Suite 600, Berkeley, CA 94704. ahmad@icsi.berkeley.edu, om@icsi.berkeley.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tishby.sst2.ps.Z, 19910611 Part II: Figure 12, Zero Entropy 0.5 1 5 10 50 0.05 0.1 0.5 1 5 REPLICA SYMMETRY BREAKING T a Part II: Figure 11, Optimal T 0.05 0.1 0.5 1 0.26 0.28 0.30 0.32 0.34 0.36 1.2 1.6 2.0 2.8 e T g Part II: Figure 10b, T=0.5 2 4 6 8 10 0.0 0.1 0.2 0.3 0.4
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tishby.sst1.ps.Z, 19910611 Submitted to Physical Review A Statistical Mechanics of Learning From Examples I. General Formulation and Annealed Approximation H. S. Seung, H. Sompolinsky Racah Institute of Physics, Hebrew University, Jerusalem 91904, Israel N. Tishby AT&T Bell Laboratories, 600 Mountain Ave., Murray Hill, NJ 07974
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fox.decomp.ps.Z, 19910617 To appear in: O. Simula (ed.) Proceedings of the International Conference on ARTIFICIAL NEURAL NET- WORKS, ICANN-91, Elsevier Science Publishers, June 1991 LEARNING BY ERROR-DRIVEN DECOMPOSITION Dieter Fox y Volker Heinze y Knut M ollery Sebastian Thrunyz Gerd Veenker y yComputer Science Department
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fahlman.cascor-tr.ps.Z, 19910619 The Cascade-Correlation Learning Architecture Scott E. Fahlman and Christian Lebiere February 14, 1990 CMU-CS-90-100 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/koch.syncron.ps.Z, 19910625 A Simple Network Showing Burst Synchronization without Frequency-Locking Christof Koch1;3 and Heinz Schuster1;2 1 Computation and Neural Systems Program, California Institute of Technology, Pasadena, California 91125 USA 2 Institut f ur theoretische Physik, Universit at Kiel, Olshausenstrasse 40, 2300
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/port.langrep.ps.Z, 19910702 Representing Aspects of Language Robert F. Port Departments of Linguistics and Computer Science port@ucs.indiana.edu Timothy van Gelder Department of Philosophy Indiana University, Bloomington, Indiana 47405 tgelder@ucs.indiana.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fritzke.linear_tsp.ps.Z, 19910702 1 FLEXMAP { A Neural Network For The Traveling Salesman Problem With Linear Time And Space Complexity Bernd FRITZKE and Peter WILKE Universit at Erlangen-N urnberg Lehrstuhl f ur Programmiersprachen Martensstr. 3 D-8520 Erlangen Germany Tel. (++49) +9131/857830 Fax (++49) +9131/39388
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/utans.bondrating.ps.Z, 19910702 To appear in the proceedings of the First International Conference on Artifical Intelligence Applications on Wall Street. IEEE Computer Society Press, Los Alamitos, CA, (1991). Selecting Neural Network Architectures via the Prediction Risk: Application to Corporate Bond Rating Prediction Joachim Utans
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plutowski.active.ps.Z, 19910709 Active selection of training examples for network learning in noiseless environments. Mark Plutowski Department of Computer Science and Engineering University of California, San Diego Halbert White Institute for Neural Computation and Department of Economics University of California, San Diego February
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plonski.nnreview.ps.Z, 19910709 \| Command Purpose \| RCS \| GENESIS \| SFINX \| \| Add/Change/Delete \| Primary means of building up network\| create \| load filename (explicit networks \| \| elements and \| is a conventional call to a 'build' \| createmap (multiple copies) \| must be 'assembled' into binary \| \|
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/berg.phrase_structure.ps.Z, 19910723 Department of Computer Science University at Albany State University of New York Learning Recursive Phrase Structure: Combining the Strengths of PDP and X-Bar Syntax TR 91-5 George Berg UNIVERSITYATALBANYSTATEUNIVERSITYOFNEWYORKHH Learning Recursive Phrase Structure: Combining the Strengths of PDP and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sloman.fbi.ps.Z, 19910730 Feature-based induction 1 1 Feature-Based Induction Steven A. Sloman University of Michigan Submitted for publication. Steven Sloman Dept. of Psychology 330 Packard Rd. Ann Arbor, MI, 48104-2994 e-mail: sloman@psych.stanford.edu Feature-based induction 2 2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mcmillan.csg.ps.Z, 19910801 - 1 -
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/whittaker.beef.ps.Z, 19910812 ULTRASONIC SIGNAL CLASSIFICATION FOR BEEF QUALITY GRADING THROUGH NEURAL NETWORKS y A. Dale Whittaker Member ASAE Bo Soon Park Member ASAE James Darrell McCauley Student Member ASAE Yanbo Huang Meat palatability is often related to the percent of intramuscular fat present in a meat cut. In fact, the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ingber.eeg.ps.Z, 19910814 Physical Review A,vol. 44 (6) (to be published 15 Sep 91) ingber@umiacs.umd.edu Statistical mechanics of neocortical interactions: Ascaling paradigm applied to electroencephalography Lester Ingber Science Transfer Corporation, P.O. Box 857, McLean, VA22101 (Received 10 April 1991) Aseries of papers has
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.multi.ps.Z, 19910815 tive task, implemented in an enumerative rather than explicit storage memory, we see a new general-purpose connectionist model beyond the categorization and associative memory of feed-forward and relaxation models, and the prediction and sequence generation of recurrent networks. Acknowledgments
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/squires.cascor.ps.Z, 19910903 Machine Learning Research Group Working Paper 91-1 EXPERIMENTAL ANALYSIS OF ASPECTS OF THE CASCADE-CORRELATION LEARNING ARCHITECTURE Charles S. Squires, Jr. Jude W. Shavlik Computer Sciences Department University of Wisconsin- Madison 1210 West Dayton Street Madison, WI 53706 squires@cs.wisc.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mozer.segment.ps.Z, 19910911 Learning to segment images using dynamic feature binding Michael C. Mozer Department of Computer Science & Institute of Cognitive Science University of Colorado Boulder, CO 80309{0430 Richard S. Zemel Department of Computer Science University of Toronto Toronto, Ontario M5S 1A4 Marlene Behrmann
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/anthony.medical.ps.Z, 19910916
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mehra.duality.ps.Z, 19910916 Principled Constructive Induction 1 Mehra et al. Principled Constructive Induction Pankaj Mehra1 Larry A. Rendell Benjamin W. Wah1 Coordinated Science Lab., Beckman Institute, Coordinated Science Lab., University of Illinois, University of Illinois, University of Illinois, Urbana, IL 61801. Urbana, IL
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.gabor.ps.Z, 19910927 Gabor Representations of Spatiotemporal Visual Images Bruce MacLennan Technical Report CS-91-144 September 13, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shultz.balance.ps.Z, 19910930 Balance scale 640 200150100500 5 10 15 20 1 2-5 6-9 10-20 Epoch Error Torque Difference Figure 4. Errors on test problems at 4 torque difference levels for 1 subject. 1 2-5 6-9 10-20 1 2 3 4 5 6 7 75th Last Torque Difference Error Epoch F(1, 42) = 140.45 Figure 5. Mean errors on test problems at 4
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shultz.stages.ps.Z, 19910930 Stages of cognitive development 109 Ordinality in the appearance of stages has been found in connectionist models, particularly in those concerned with the balance scale. The typical pattern was to progress through all four stages in the correct order, with some minimal skipping and regression (Shultz &
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smagt.rtcontrol.ps.Z, 19911001 A real-time learning neural robot controller P. Patrick van der Smagty Ben J. A. Kr ose University of Amsterdam Department of Computer Systems Kruislaan 403, 1098 SJ Amsterdam THE NETHERLANDS email: smagt@fwi.uva.nl
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gee.opt_map.ps.Z, 19911004 1 1 Email: ahg/svb10/rwp @eng.cam.ac.uk For several years now there has been much research interest in the use of Hopfield networks to solve combinatorial optimization problems. Although initial results were disappointing, it has since been demonstrated how modified network dynamics and better problem
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bessiere.nerves.ps.Z, 19911008 Part 1 Introduction to deliverable: purpose and approach .......................................................................... 1 1. Introduction .............................................................................................................. 1 2. Original description of the task
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bessiere.cognitiva90.ps.Z, 19911008 VERS UN PARADIGME SYNTHETIQUE DE LA COGNITION : L'INFERENCE PROBABILISTE TOWARD A SYNTHETIC COGNITIVE PARADIGM: PROBABILISTIC INFERENCE Pierre Bessi re1 RESUME : Les sciences cognitives connaissent actuellement un renouveau certain. Elles sont la crois e des chemins d'id es venues de domaines
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/towell.interpretation.ps.Z, 19911008 Machine Learning Research Group Working Paper 91-4 The Extraction of Refined Rules from Knowledge-Based Neural Networks Geoffrey G. Towell Jude W. Shavlik University of Wisconsin \| Madison 1210 West Dayton Street Madison, Wisconsin 53706 (608) 262-6613 ftowell, shavlikg@cs.wisc.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bessiere.innc90.ps.Z, 19911008 A VIRTUAL MACHINE MODEL FOR ARTIFICIAL NEURAL NETWORK PROGRAMMING Pierre Bessi re1, Ali Chams2 & Traian Muntean3
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/scott.nnpid.ps.Z, 19911008 Machine Learning Research Group Working Paper 91-3. Refining PID Controllers using Neural Networks Gary M. Scott Department of Chemical Engineering 1415 Johnson Drive University of Wisconsin Madison, WI 53706 Jude W. Shavlik y Department of Computer Sciences 1210 W. Dayton Street University of Wisconsin
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tzirkel.control_tr81.ps.Z, 19911008 The first author is supported by Trinity College Cambridge and the Committee of Vice-Chancellors and Principals of the UK. CUED/F-INFENG/TR.81 Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England July 1991 E. Tzirkel-Hancock & F. Fallside email: et@eng.cam.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclin.fskbann.ps.Z, 19911008 Machine Learning Research Group Working Paper 91-2 Refining Algorithms with Knowledge-Based Neural Networks: Improving the Chou-Fasman Algorithm for Protein Folding* Richard Maclin Jude W. Shavlik Computer Sciences Dept. University of Wisconsin 1210 W. Dayton St. Madison, WI 53706 email:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bessiere.acm-ics91.ps.Z, 19911008
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.css.ps.Z, 19911010 Continuous Symbol Systems The Logic of Connectionism Technical Report CS-91-145 Bruce MacLennan Computer Science Department University of Tennessee, Knoxville October 7, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/robinson-tr82.ps.Z, 19911014 Recurrent Error Propagation Networks have been shown to give good performance on the speaker independent phone recognition task in comparison with other methods (Robinson and Fallside, 1991). This short report describes several recent improvements made to the existing recogniser for the TIMIT database.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nowlan.soft-share.ps.Z, 19911019 Simplifying Neural networks by Soft Weight-Sharing Steven J. Nowlan Computational Neuroscience Laboratory The Salk Institute P.O. Box 5800 San Diego, CA 92186-5800 Geoffrey E. Hinton Department of Computer Science University of Toronto Toronto, Canada M5S 1A4
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pearlmutter.soft-share.soft-share.ps.Z, 19911022 It was a joke, dummy!
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zeidenberg.containment.ps.Z, 19911028 Implementing Spatial Relations in Neural Nets: Figure/Ground and Containment Matthew Zeidenberg University of Wisconsin{Madison and Electrotechnical Laboratory, Japan October 1991 1 Introduction There is, no doubt, a division among mental functions. Some are learned, while some are innate. I argue that
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/polycarpou.stability.ps.Z, 19911101 Identification and Control of Nonlinear Systems Using Neural Network Models: Design and Stability Analysis by Marios M. Polycarpou and Petros A. Ioannou Report 91-09-01 September 1991 Identification and Control of Nonlinear Systems Using Neural Network Models: Design and Stability Analysis Marios M.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sanner.adcontrol_9109.ps.Z, 19911111 NSL-910901, Sept. 1991 To appear: IEEE CDC, Dec. 1991 Stable Adaptive Control and Recursive Identification Using Radial Gaussian Networks Robert M. Sanner and Jean-Jacques E. Slotine Nonlinear Systems Laboratory Massachusetts Institute of Technology Cambridge, MA 02139 USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sanner.adcontrol_9103.ps.Z, 19911111 NSL-910303, March 1991 Also appears: Proc. ACC, June 1991 Direct Adaptive Control Using Gaussian Networks Robert M. Sanner and Jean-Jacques E. Slotine Nonlinear Systems Laboratory Massachusetts Institute of Technology Cambridge, MA 02139
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sanner.adcontrol_9105.ps.Z, 19911111 NSL-910503. May, 1991. Gaussian Networks for Direct Adaptive Control Robert M. Sanner and Jean-Jacques E. Slotine Nonlinear Systems Laboratory Massachusetts Institute of Technology Cambridge, MA 02139
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plaut.dyslexia.ps.Z, 19911112 Deep Dyslexia: A Case Study of Connectionist Neuropsychology David C. Plaut Department of Psychology Carnegie Mellon University dcp@cs.cmu.edu Tim Shallice Department of Psychology University College London ucjtsts@ucl.ac.uk November, 1991 Technical Report CRG-TR-91-3 Connectionist Research Group
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.cckr.ps.Z, 19911127 Characteristics of Connectionist Knowledge Representation Technical Report CS-91-147 Bruce MacLennan Computer Science Department University of Tennessee, Knoxville November 26, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/siegelman.turing.ps.Z, 19911204 Report SYCON-91-11 ON THE COMPUTATIONAL POWER OF NEURAL NETS Hava T. Siegelmann, Department of Computer Science Eduardo D. Sontag, Department of Mathematics Rutgers University, New Brunswick, NJ 08903 E-mail: siegelma@paul.rutgers.edu, sontag@hilbert.rutgers.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/desa.top_down.ps.Z, 19911211 Top-down Teaching Enables Non-trivial Clustering via Competitive Learning Virginia de Sa Dana Ballard The University of Rochester Computer Science Department Rochester, New York 14627 Technical Report 402 November 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sjogaard.concept.ps.Z, 19911211 C APPENDIX 81 C Appendix This appendix contains all the data from Experiment 2 described in Section 5.5. Table 12 and 13 show the most important figures and the percentages of correctly classified test patterns for the HCCA and the 2CCA network, respectively. The first three columns show the number of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.comparison.ps.Z, 19911212 The MONK's Problems A Performance Comparison of Different Learning Algorithms S.B. Thrun, J. Bala, E. Bloedorn, I. Bratko, B. Cestnik, J. Cheng, K. De Jong, S. D<=zeroski, S.E. Fahlman, D. Fisher, R. Hamann, K. Kaufman, S. Keller, I. Kononenko, J. Kreuziger, R.S. Michalski, T. Mitchell, P. Pachowicz, Y.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ingber.mnn.ps.Z, 19911217 Generic mesoscopic neural networks based on statistical mechanics of neocortical interactions Lester Ingber Science Transfer Corporation, P.O. Box 857, McLean, VA22101 ingber@umiacs.umd.edu Aseries of papers has developed a statistical mechanics of neocortical interactions (SMNI), deriving aggregate
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/buntine.bayes.ps.Z, 19911217 Buntine and Weigend Bayesian Back-Propagation 2 Contents 1 Introduction 2 2 On Bayesian methods 3 3 Multi-Layer networks 5 3.1 Notation : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 5 3.2 Probabilistic neural networks : : : : : : : : : : : : : : : : : : : : : : : : : : :
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/buntine.treecode.ps.Z, 19911217 About the IND Tree Package Wray Buntine, RIACS NASA Ames Research Center Mail Stop 269-2 Moffet Field, CA 94035 September 29, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schmidhuber.factorial.ps.Z, 19911218 LEARNING FACTORIAL CODES BY PREDICTABILITY MINIMIZATION (compact version of TR CU-CS-565-91) J urgen Schmidhuber Department of Computer Science University of Colorado Campus Box 430, Boulder, CO 80309, USA yirgan@cs.colorado.edu December 18, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/reilly.parser.ps.Z, 19911219 A CONNECTIONIST TECHNIQUE FOR ON-LINE PARSING Ronan Reilly Educational Research Centre St Patrick's College, Dublin 9 Connectionist Parsing
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/marshall.steering.ps.Z, 19920103 Michalski, A., Gerstein, G.L., Czarkowska, J., & Tarnecki, R. (1983). Interactions Between Cat Striate Cortex Neurons." Experimental Brain Research, 51, 97{107. Michotte, A., Thinges, G., & Crabbe, G. (1964). Les Complements Amodaux des Structures Perceptives (Studia Psychologia)." Louvain:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.nips91.ps.Z, 19920113 To appear in: Advances in Neural Information Processing Systems 4 J.E. Moody, S.J. Hanson, and R.P. Lippmann (eds.) Morgan Kaufmann, San Mateo, CA, 1992 Active Exploration in Dynamic Environments Sebastian B. Thrun School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/NIPS91/marshall.abstracts.ps.Z, 19920115 NIPS*91 Post-Conference Workshop on Self-Organization and Unsupervised Learning in Vision December 6{7, 1991 in Vail, Colorado Workshop Chair: Jonathan A. Marshall, Ph.D. Department of Computer Science, CB 3175, Sitterson Hall University of North Carolina, Chapel Hill, NC 27599-3175, U.S.A.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/krogh.weight-decay.ps.Z, 19920115 therefore it is strictly only valid in a little neighborhood around that vector. The improvement from a weight decay was also tested by simulations. For the NetTalk data it was shown that a weight decay can decrease the generalization error (squared error) and also, although less significantly, the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gascuel.hopfield-chip.ps.z, 19920124 A digital CMOS fully connected neural network with in-circuit learning capability and automatic identification of spurious attractors. Jean-Dominique Gascuel, Michel Weinfeld, Sami Chakroun Ecole polytechnique Laboratoire d'informatique F-91128 Palaiseau Cedex France gascuel@polytechnique.fr
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lacher.rapprochement.ps.Z, 19920128 Expert Networks: Paradigmatic Conflict, Technological Rapprochementy R. C. Lacherz Department of Computer Science Mail Code B-173 Florida State University Tallahassee, FL 32306 USA lacher@cs.fsu.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/moody.p_effective.ps.Z, 19920130 Appears in J.E. Moody, S.J. Hanson, and R.P. Lippmann, editors, Advances in Neural Information Processing Systems 4, Morgan Kaufmann Publishers, San Mateo, CA, 1992. The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems John E. Moody
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/giles.nips91.ps.Z, 19920203 proaches can model grammars with large numbers of states and establish a theoretical and experimental relationship between DFA state capacity and neural net size. Acknowledgments The authors acknowledge useful and helpful discussions with E. Baum, M. Goudreau, G. Kuhn, K. Lang, L. Valiant, and R.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jordan.forward-models.ps.Z, 19920203 MIT Center for Cognitive Science Occasional Paper #40 Forward models: Supervised learning with a distal teacher Michael I. Jordan Department of Brain and Cognitive Sciences Massachusetts Institute of Technology David E. Rumelhart Department of Psychology Stanford University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/xu.on_reps.ps.Z, 19920205 On Representations 1 On Representations Bo Xu1 Department of Physiology and Biophysics School of Medicine Indiana University itgt500@indycms.iupui.edu Liqing Zheng Department of Electrical Engineering Purdue University, Indianapolis
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/NIPS91/vlsi.summary.ps, 19920209 NIPS*91 VLSI Workshop Summary Organized by Clifford Lau, Office of Naval Research Jim Burr, Stanford University February 8, 1992 1 Introduction This is a report on the NIPS Post-Conference Workshop on VLSI Neural Networks and Neurocomputers, which was held at Vail, CO on December 6-7, 1991. 1 The
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thgoh.fuzzy.ps.Z, 19920212 Learning Algorithm for the Enhanced Fuzzy Perceptron TH Goh, PZ Wang, HC Lui Institute of Systems Science National University of Singapore Heng Mui Keng Terrace Kent Ridge, S0511 Singapore Email : ISSGTH @ NUSVM, thgoh@iss.nus.sg December 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/usher.smemory.ps.Z, 19920212 7200{7204. Schillen,T.B. & Konig,P. 1991. Stimulus-dependent assembly formation of oscillatory responses: I. Synchronization, Neural Comp. 3, 155{166. Wang,D., Buhmann,J. & von der Malsburg,C. 1990. Pattern segmentation in associative memory. Neural Comp. 2, 94{106. Wilson,H.R. & Cowan,J.D. 1972.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/battiti.second.ps.Z, 19920212 1 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sperduti.bp+.fig5.ps.Z, 19920217 400 800 1200 1600 20000 1e-03 1e-02 1e-01 1e+00 1e+01 1e+02 Number of Epochs Error 8x8 DOT NUMERIC FONT LEARNING NETWORK 64-6-10 h = 2.2 h = 2.0 h = 1.2 h = 1.5 (e = 0) FIGURE 5. Mean learning curves for the 8x8 dot numeric font learning obtained using the standard back propagation. Each curve refers to
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sperduti.bp+.fig3.ps.Z, 19920217 1e-02 1e-03 1e-01 1e+00 1e+01 1e-04 FOUR BITS PARITY PROBLEM NETWORK 4-6-1 1000 2000 3000 4000 5000 Number of Epochs Error h = 0.5 e = 0.3 m = 0.9 b c d a FIGURE 3. Mean learning curves for the four bits parity problem. Curves (a) and (c) refer to the extended back propagation with initial steepness
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sperduti.bp+.tr.ps.Z, 19920217 Extended Back Propagation 1 Speed Up Learning and Network Optimization With Extended Back Propagation Alessandro SPERDUTI, Antonina STARITA Department of Computer Science Corso Italia, 40 - 56100 - PISA ITALY
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sjoberg.overtraining.ps.Z, 19920217 Overtraining, Regularization, and Searching for Minimum in Neural Networks J. Sj oberg, L. Ljung Department of Electrical Engineering Link oping University S-581 83 Link oping, Sweden Phone: +46 13 281890 E-mail: sjoberg@isy.liu.se February 17, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sperduti.bp+.fig6.ps.Z, 19920217 1e-03 1e-02 1e-01 1e+00 1e+01 1e+02 8x8 DOT NUMERIC FONT LEARNING NETWORK 64-6-10 400 800 1200 1600 2000 Number of Epochs Error e = 0.1 e = 0.3 e = 0.6 e = 0.9 (h = 1.5) FIGURE 6. Mean learning curves for the 8x8 dot numeric font learning obtained by using extended back propagation. Each curve was
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smieja.plastic.ps.Z, 19920219 Hyperplane Spin" Dynamics, Network Plasticity and Back-Propagation Learning Frank J. Smieja y German National Research Centre for Computer Science (GMD), Schloss Birlinghoven, 5205 St. Augustin 1, Germany. November 28, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lovell.errorbounds.ps.Z, 19920226 Error and Variance Bounds on Sigmoidal Neurons with Weight and Input Errors David Lovell, Peter Bartlett & Tom Downs Intelligent Machines Laboratory, Department of Electrical Engineering University of Queensland, Queensland 4072, Australia
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kaplan.trace.ps.Z, 19920227 Activity in Cognitive Elements 48 6 TRACE has been simulated with a variety of input equations with negligible difference in results. Activity in Cognitive Elements 47 sequence (and likewise for the relationship between the phase sequence and the phase cycle). Since Hebb considered the cell assembly to
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/xu.ppnn2.ps.Z, 19920304 Parallel Probabilistic Neural Network (PPNN) 1 Parallel Probabilistic Neural Network (PPNN) Bo Xu1 Indiana University Liqing Zheng Purdue University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lovell.closed-form.ps.Z, 19920305 A Note on a Closed-Form Training Algorithm for the Neocognitron David Lovell, Ah Chung Tsoi & Tom Downs Intelligent Machines Laboratory, Department of Electrical Engineering University of Queensland, Queensland 4072, Australia
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.beyond.ps.Z, 19920311 Beyond Associative Memories: Logics and Variables in Connectionist Models Ron Sun Honeywell SSDC 3660 Technology Drive Minneapolis, MN 55418 January 29, 1992 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schwarze.gentree.ps.Z, 19920311 Generalization in a Large Committee Machine H. Schwarze and J. Hertz CONNECT, The Niels Bohr Institute and Nordita Blegdamsvej 17, DK-2100 Copenhagen O, Denmark March 6, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.inh.ps.Z, 19920312 An Efficient Feature-based Connectionist Inheritance Scheme Ron Sun Honeywell SSDC 3660 Technology Drive Minneapolis, MN 55418 March 11, 1992 1 Contents 1 Introduction 4 2 Basic Inheritance 7 2.1 Two Types of Links : : : : : : : : : : : : : : : : : : : : : : : : : : : 7 2.2 A Set of Benchmarks : : : : :
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.evidence.ps.Z, 19920313 A RIGOROUS INVESTIGATION OF EVIDENCE AND OCCAM FACTORS IN BAYESIAN REASONING by David H. Wolpert The Santa Fe Institute, 1660 Old Pecos Trail, Suite A, Santa Fe, NM, 87501 (dhw@sfi.santafe.edu)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smieja.reflect.ps.Z, 19920313 Reflective Modular Neural Network Systems F.J. Smieja smieja@gmdzi.uucp H. M uhlenbein muehlen@gmdzi.uucp German National Research Centre for Computer Science (GMD), Schloss Birlinghoven, 5205 St. Augustin 1, Germany. March 13, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/marti.ga2.ps.Z, 19920316 Genetically Generated Neural Networks II: Searching for an ptimal epresentation CAS/CNS-TR-92-015 Leonardo Mart Boston University Center for Adaptive Systems 111 Cummington Street Boston, MA 02215 lmarti@cns.bu.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/marti.ga1.ps.Z, 19920316 enetically enerate eural et or s I: e resentational ects CAS/CNS-T -92-014 Leonardo art Boston niversity Center for Adaptive Systems 111 Cummington Street Boston, A 02215 lmarti cns.bu.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smith.components.ps.Z, 19920317 1 1 A flexible system is one in which simple changes of functionality and performance can be implemented without major redesign. G. Smith guy@minster.york.ac.uk J. Austin austin@minster.york.ac.uk Advanced Computer Architecture Group Department of Computer Science University of York York UK This paper
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wu.nlpcoding.ps.Z, 19920323 CUED/F-INFENG/TR.94 Submitted to IEEE Transactions on Signal Processing. Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England March 1992 Lizhong Wu & Frank Fallside Email: lzw@eng.cam.ac.uk or fallside@eng.cam.ac.uk Fully Vector Quantized Neural Network-Based
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.exploration-overview.ps.Z, 19920326 To appear in: Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Approaches David A. White and Donald A. Sofge (editors) Van Nostrand Reinhold, Florence, Kentucky 41022 (publisher) THE ROLE OF EXPLORATION IN LEARNING CONTROL Sebastian B. Thrun Department of Computer Science Carnegie-Mellon
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.explor-reinforcement.ps.Z, 19920326 Efficient Exploration In Reinforcement Learning Sebastian B. Thrun January 1992 Technical report CMU-CS-92-102 School of Computer Science Carnegie-Mellon University Pittsburgh, Pennsylvania 15213-3890 e-mail: thrun@cs.cmu.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/miller.intro.ps.Z, 19920402 The Use of odels in the eurosciences Introduction for Seminars in the Neurosciences, Vol. 4, No. 1, Feb. 1992 (pp. 1-3) Kenneth D. Miller Division of Biology Caltech 216-76 Pasadena, CA 91125 ken@cns.caltech.edu Few things are easier to speculate about than the workings of the brain and the mind, but
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/omlin.hints.ps.Z, 19920414 Training Second-Order Recurrent Neural Networks using Hints Christian W. Omlin Computer Science Department Rensselaer Polytechnic Institute Troy, N.Y. 12180 USA C. Lee Giles NEC Research Institute 4 Independence Way Princeton, N.J. 08540 USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lovell.neocog.ps.Z, 19920414 The Performance of the Neocognitron with Various S-Cell and C-Cell Transfer Functions David R. Lovell & Ah Chung Tsoi Intelligent Machines Laboratory, Department of Electrical Engineering, University of Queensland, Queensland 4072, Australia April 14, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mccauley.beef.ps.Z, 19920420 Shorter version submitted to Transactions of ASAE. Fat Estimation in Beef Ultrasound Images Using Texture and Adaptive Logic Networks James Darrell McCauley Brian R. Thaney A. Dale Whittakerz
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/finch.hybrid.ps.Z, 19920421 A Hybrid Approach to the Automatic Learning of Linguistic Categories Steven Finch & Nick Chater y October 27, 1991
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.reichenbach-2.ps.Z, 19920421 36 iii) A meta event space. Consider again the event space U. Equation (3.1) implicitly tells us the optimal hypothesis function for any training set, as a function of P(f \| q). Unfortunately, we don t know P(f \| q) a priori - it s determined by the physical universe. As was mentioned in section III,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.reichenbach-1.ps.Z, 19920421 ON THE CONNECTION BETWEEN IN-SAMPLE TESTING AND GENERALIZATION ERROR. by David H. Wolpert1,2 1 - Theoretical Division and Center for Nonlinear Studies, MS B213, LANL, Los Alamos, NM, 87545, (dhw@tweety.lanl.gov) 2 - The Santa Fe Institute, 1660 Old Pecos Trail, Suite A, Santa Fe, NM, 87501 (current
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/neal.hmc.ps.Z, 19920422 Bayesian Training of Backpropagation Networks by the Hybrid Monte Carlo Method Radford M. Neal Technical Report CRG-TR-92-1 Connectionist Research Group Department of Computer Science University of Toronto e-mail: radford@cs.toronto.edu 10 April 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gee.energy_fns.ps.Z, 19920423 A. H. Gee & R. W. Prager March 1992 Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England Email: ahg/rwp @eng.cam.ac.uk ALTERNATIVE ENERGY FUNCTIONS FOR OPTIMIZING NEURAL NETWORKS CUED/F-INFENG/TR 95 1 1 Email: ahg/rwp @eng.cam.ac.uk When feedback neural networks are
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.cogsci92.ps.Z, 19920430 Fuzzy Evidential Logic: A Model of Causality for Commonsense Reasoning Ron Sun Honeywell SSDC Minneapolis, MN 55418
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.ka.ps.Z, 19920430 A Connectionist Model for Commonsense Reasoning Incorporating Rules and Similarities Ron Sun Honeywell SSDC 3660 Technology Dr. Minneapolis, MN 55413 rsun@orion.ssdc.honeywell.com (612) 782-7379 Running Title: Connectionist reasoning bigskip bigskip To appear in: Knowledge Acquisition. Academic Press,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.stack_gen.ps.Z, 19920506 STACKED GENERALIZATION by David H. Wolpert Complex Systems Group, Theoretical Division, and Center for Non-linear Studies, MS B213, LANL, Los Alamos, NM, 87545 (dhw@tweety.lanl.gov) (505) 665-3707. This work was performed under the auspices of the Department of Energy. LA-UR-90-3460 2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shultz.dissonance.ps.Z, 19920511 Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society 1992. Hillsdale, NJ: Erlbaum. A Constraint Satisfaction Model of Cognitive Dissonance Phenomena Thomas R. Shultz Mark R. Lepper Department of Psychology Department of Psychology McGill University Stanford University 1205
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schmidt.balance.ps.Z, 19920515 Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society 1992. Hillsdale, NJ: Erlbaum. An Investigation of Balance Scale Success William C. Schmidt and Thomas R. Shultz Department of Psychology McGill University 1205 Penfield Avenue Montr al, Qu bec, Canada H3A 1B1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maskara.cogsci92.ps.Z, 19920515 Forced Simple Recurrent Neural Networks and Grammatical Inference Arun Maskara New Jersey Institute of Technology Department of Computer and Information Sciences University Heights, Newark, NJ 07102 arun@hertz.njit.edu Andrew Noetzel The William Paterson College Department of Computer Science Wayne, NJ
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wasserman.mult_mean.ps.Z, 19920515 This article is in press in Biological Signals published by Karger. It should be published in late 1992. Isomorphism, Task Dependence, and the Multiple Meaning Theory of Neural Coding Gerald S. Wasserman Sensory Coding Laboratory Department of Psychological Sciences Purdue University West Lafayette,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stucki.frame.ps.Z, 19920515
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/das.cfg_induction.ps.Z, 19920518 Learning Context-free Grammars: Capabilities and Limitations of a Recurrent Neural Network with an External Stack Memory Sreerupa Das Department of Computer Science University of Colorado Boulder, CO 80309 rupa@cs.colorado.edu C. Lee Giles NEC Research Institute 4 Independence Way Princeton, NJ 08540
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plaut.relearning.ps.Z, 19920518 Relearning after Damage in Connectionist Networks: Implications for Patient Rehabilitation David C. Plaut Department of Psychology Carnegie Mellon University Pittsburgh, PA 15213{3890 plaut+@cmu.edu To appear in Proceedings of the 14th Annual Conference of the Cognitive Science Society, Bloomington, IN,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fontaine.charrec.ps.Z, 19920522 Character Recognition Using A Modular Spatiotemporal Connectionist Model Thomas Fontaine and Lokendra Shastri Computer and Information Science Department University of Pennsylvania Philadelphia, PA 19104-6389
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gee.poly.ps.Z, 19920529 1 1 Email: ahg/rwp @eng.cam.ac.uk The often disappointing performance of optimizing neural networks can be partly attributed to the rather manner in which problems are mapped onto them for solution. In this paper a rigorous mapping is described for quadratic 0-1 programming problems with linear equality
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pet.knap.ps.Z, 19920602 March 1992 LU TP 92-11 Neural Networks for Optimization Problems with Inequality Constraints - the Knapsack Problem Mattias Ohlsson1, Carsten Peterson2 and Bo S oderberg3 Department of Theoretical Physics, University of Lund S olvegatan 14A, S-22362 Lund, Sweden Submitted to Neural Computation
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maa.compression.ps.Z, 19920603 - 1 - 1. Introduction Image compression is essential for applications that demand a high efficiency in storing and transmitting images. Such applications include medical images database, pictorial catalog archives, facsimile transmission, video conferencing, and multimedia systems, just to name a few.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/eldracher.tde.ps.Z, 19920605 Classification of Non-Linear-Separable Real-World-Problems Using -Rule, Perceptrons, and Topologically Distributed Encoding Martin Eldracher y Technische Universit at M unchen Institut f ur Informatik Arcisstr.21, 8000 M unchen 2, Germany e-mail: eldrache@informatik.tu-muenchen.de
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dasgupta.approx.ps.Z, 19920611 Efficient Approximation with Neural Networks: A Comparison of Gate Functions Bhaskar DasGuptay Georg Schnitgerz Department of Computer Science The Pennsylvania State University University Park PA 16802
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/albertini.ident.ps.Z, 19920611 Report SYCON-92-03 FOR NEURAL NETWORKS, FUNCTION DETERMINES FORM Francesca Albertini Eduardo D. Sontag Department of Mathematics Rutgers University, New Brunswick, NJ 08903 E-mail: albertin@hilbert.rutgers.edu, sontag@hilbert.rutgers.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/unni.alopex.ps.Z, 19920618 In Proceedings of IJCNN, pp. I926 I931 (IEEE Press, 1992) Fig. 4a. Error convergence of the encoder networks with log error Fig. 4b. Error convergence for the encoder networks with square error DISCUSSION We presented a universal learning algorithm for neural networks. The algorithm can be used for
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fontaine.gradcm2.ps.Z, 19920707 Thomas Fontaine Computer and Information Science Department University of Pennsylvania Philadelphia, PA 19104-6389
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smolensky.principles.ps.Z, 19920708
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/murata.nic.ps.Z, 19920713 Network Information Criterion \| Determining the Number of Hidden Units for an Artificial Neural Network Model Noboru Murata, Shuji Yoshizawa, Shun-ichi Amari, University of Tokyo , June 22, 1992.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yao.eann.ps.Z, 19920723 A Review of Evolutionary Artificial Neural Networks12 Xin Yao Commonwealth Scientific and Industrial Research Organisation Division of Building, Construction and Engineering PO Box 56, Highett, Victoria 3190 AUSTRALIA 1Accepted by International Journal of Intelligent Systems, to appear. 2Part of this
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yao.complex.ps.Z, 19920723 Finding Approximate Solutions to NP-Hard Problems by Neural Networks Is Hard y Xin Yaoz Computer Sciences Laboratory Research School of Physical Sciences and Engineering The Australian National University GPO Box 4, Canberra, ACT 2601, Australia
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/golden.gbsb.ps.Z, 19920724 Generalized Brain-State-in-a-Box 1 Stability and Optimization Analyses of the Generalized Brain-State-in-a-Box Neural Network Model Richard M. Golden University of Texas at Dallas Richard M. Golden, University of Texas at Dallas, School of Human Development, GR41, Box 830688, Richardson, Texas, 75083
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yao.sa_en.ps.Z, 19920728 Simulated Annealing with Extended Neighbourhood1 Xin Yao Computer Sciences Laboratory Research School of Physical Sciences and Engineering The Australian National University GPO Box 4, Canberra, ACT 2601 AUSTRALIA e-mail: xin@cslab.anu.edu.au Fax: (+61 6)/(06)249 1884 1In International Journal of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yun.cs.ps.Z, 19920814 Training Algorithms for Limited Precision Feedforward Neural Networks Yun Xie Department of Electronic Engineering, Tsinghua University, Beijing 100084, P.R.China Marwan A. Jabri Department of Electrical Engineering The University of Sydney N.S.W. 2006, Australia SEDAL Technical Report No. 1991-8-3
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/darken.learning_rates.ps.Z, 19920817 Revised and expanded version, August 1992. Original appears in Neural Networks for Signal Processing 2 \| Proceedings of the 1992 IEEE Workshop, IEEE Press, 445 Hoes Lane, Piscataway, NJ 08854. LEARNING RATE SCHEDULES FOR FASTER STOCHASTIC GRADIENT SEARCH Christian Darken*, Joseph Chang z and John
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/frasconi.nfa.ps.Z, 19920824 Injecting Nondeterministic Finite State Automata into Recurrent Neural Networks Paolo Frasconi Marco Gori Giovanni Soda Dipartimento di Sistemi e Informatica Via di Santa Marta 3 - 50139 Firenze - Italy Tel. (+39) 55-4796265 - Fax (+39) 55-4796363 e-mail : ffrasconi,marcog@ingfi1.cineca.it
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/james.nnsim.ps.Z, 19920824 1 Design of Low-cost, Real-time Simulation Systems for Large Neural Networks by Mark R. James A thesis submitted to fulfil the requirements of the degree of Master of Science, at the University of Sydney. JANUARY, 1992 2 /
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mcgraw.letter_spirit.ps.Z, 19920901 Letter Spirit: Recognition and Creation of Letterforms Based on Fluid Concepts Gary McGraw Center for Research on Concepts and Cognition Department of Computer Science Indiana University, Bloomington, Indiana 47405 gem@cogsci.indiana.edu June 11, 1992 1 Creativity and Artificial Intelligence The Letter
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stork.obs.ps.Z, 19920914 To appear in Neural Information Processing Systems-92 ) ORAL-Algorithms and Architectures Second Order Derivatives for Network Pruning: Optimal Brain Surgeon Babak Hassibi and David G. Stork Ricoh California Research Center 2882 Sand Hill Road, Suite 115 Menlo Park, CA 94025-7022 stork@crc.ricoh.com and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wen.sgnt-perf.ps.Z, 19920917 Some Performance Comparisons for Self-Generating Neural Tree W.X. Wen, A. Jennings, H. Liu, and V. Pang AISS/TSSS, Telecom Research Labs. Clayton, Victoria 3168, Australia (in Proc. IJCNN'92, Beijing, China)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wen.sgnt-sonn.ps.Z, 19920917 A Comparative Study between SGNT and SONN W.X. Wen, V. Pang, and A. Jennings AISS/TSSS, Telecom Research Labs. Clayton, Victoria 3168, Australia (To apear in Proc. AI'92, Hobart, Australia, Nov. 1992)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wen.sgnt-learn.ps.Z, 19920917 Learning a Neural Tree Wilson X. Wen Andrew Jennings Huan Liu AI Systems, Telecom Research Laboratories 770 Blackburn Rd, Clayton, Victoria 3168, Australia (in Proc. IJCNN'92, Beijing, China)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schwarze.committee.ps.Z, 19920921 Generalization in Fully Connected Committee Machines H. Schwarze and J. Hertzy CONNECT, The Niels Bohr Institute and Nordita Blegdamsvej 17, DK-2100 Copenhagen O, Denmark September 17, 1992
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR22.ps.gz, 19920921 Distributed Rule Monitoring in Active Databases and Its Performance Analysis Ing-Miin Hsu, Mukesh Singhal, Ming T. Liu Department of Computer and Information Science The Ohio State University 2036 Neil Avenue Mall Columbus, Ohio 43210 August 10, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/speh.neuralmg.ps.Z, 19920923 DESY 92 126 ISSN 0418 9833 September 1992 Neural multigrid for gauge theories and other disordered systems M. B aker, T. Kalkreuter, G. Mack and M. Speh II. Institut f ur Theoretische Physik, Universit at Hamburg, Luruper Chaussee 149, 2000 Hamburg 50
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1991/TR5.ps.gz, 19920924 1 A stract We identify Witness reduction" as the underlying theme of several recent results in complexity theory. These include Toda's result that PH BP: P , the collapsing" of PH into P with high probability; Toda and Ogiwara's results which collapses" PH into various counting classes with high
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR07.ps.gz, 19920929 Stephen K. Park and Keith W. Miller. Random number generators: Good ones are hard to find. Communications of the ACM, 31(10):1192 1201, October 1988. Howard J. Siegel, Wayne G. Nation, Clyde P. Kruskal, and Leonard M. Napolitano. Using the multistage cube network topology in parallel
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jang.fuzzy.ps.Z, 19920930 1 1 Self-Learning Fuzzy Controllers Based on Temporal Back Propagation Jyh-Shing R. Jang Department of Electrical Engineering and Computer Science University of California, Berkeley, CA 94720 jang@diva.berkeley.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.flexcomp.ps.Z, 19921002 Research Issues in Flexible Computing Two Presentations in Japan Bruce J. MacLennan Computer Science Department University of Tennessee, Knoxville
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jang.rbfn_fuzzy.ps.Z, 19921005 1 1 Functional Equivalence between Radial Basis Function Networks and Fuzzy Inference Systems J.-S. Roger Jang and C.-T Sun Department of Electrical Engineering and Computer Science University of California, Berkeley, CA 94720 jang@diva.berkeley.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR25.ps.gz, 19921006 The Global Flush communication primitive allows the sender to order receipt of a message with respect to receipt of other messages. Use of this primitive provides an elegant way to reason about message orderings (as it allows a process to deduce the receipt event orderings at other processes), simpli es
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/TR37-1989.ps.gz, 19921008 The ALPS Kernel Prasad R. Vishnubhotla, Manas Mandal, John R. Mudd, Andreas Mitschele-Thiel, Mahendra Ramachandran, Chandrasekhar Gollamudi, Kalluri Eswar, Yow-Wei Yao, Anita Kulshreshtha, Davender Babbar and Chien-Chiao Wu Department of Computer and Information Science The Ohio State University 2036
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jang.adaptive_fuzzy.ps.Z, 19921012 1 1 ANFIS: Adaptive-Network-Based Fuzzy Inference System Jyh-Shing Roger Jang Department of Electrical Engineering and Computer Science University of California, Berkeley, CA 94720
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.variable.ps.Z, 19921013 On Variable Binding in Connectionist Networks Ron Sun Department of Computer Science The University of Alabama Tuscaloosa, AL 35487 RUNNING HEAD: variable binding KEY WORDS: connectionism, variable binding, logic, rule, network. To appear in: Connection Science, 1992 1
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR08.ps.gz, 19921013 his paper presents a process ased d namic arrier scheme hich can e implemented on large scale shared memor architectures t improves upon the d namic arrier s nchroni ation scheme ased on group loc s proposed Dimitrovs 5 he set of processes hich meet at a arrier is determined from the semantics of the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.inheritance.ps.Z, 19921013 An Efficient Feature-based Connectionist Inheritance Scheme Ron Sun Department of Computer Science The University of Alabama Tuscaloosa, AL 35487 To appear in: IEEE Transaction on System, Man and Cybernetics 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.fieldcompbrain.ps.Z, 19921014 Field Computation in the Brain Bruce MacLennany CS-92-174
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR14.ps.gz, 19921015 a i arall l a i s l i r c ss r rc i c r s si ri c s ica i Loren c wie ert . . Ja asi a e art ent of o uter an Infor ation cience e io tate niversit olu us, io 21 -12 ail: loren or ja asi cis.o io-state.e u cto er 1 , 1 2
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR02.ps.gz, 19921021 or ci ss - i ori or is ri r i io c io e - , - ee se , e e e r e er r e e e e ers e e. s, e : - - : , se , s. -s e.e er , s Inde terms: Distributed systems, termination detection, algorithms, message complexity. i 1 Introduction In a distributed system, a number of processes cooperate and communicate
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.bounds.ps.Z, 19921023 Bounds for the Computational Power and Learning Complexity of Analog Neural Nets (Extended Abstract) Wolfgang Maass* Institute for Theoretical Computer Science Technische Universitaet Graz Klosterwiesgasse 32/2 A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at October 23, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/linden.disc.ps.Z, 19921023 On Discontinuous Q-Functions in Reinforcement Learning Alexander Linden AI Research Division German National Research Center for Computer Science (GMD) P. O. Box 1316 W-5205 Sankt Augustin Germany email: Alexander.Linden@gmd.de
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR27.ps.gz, 19921026 eywords: Computational Complexity, Function classes, Closure properties. 1 Intro uction One of the most important issues of complexity theory has been the closure of language classes under various operations such as union and intersection, and the closure of function classes under functions such as
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.dendnet.ps.Z, 19921027 Information Processing in the Dendritic Net Bruce MacLennany CS-92-180
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/siegelmann.analog.ps.Z, 19921102 Report SYCON-92-05 NEURAL NETWORKS WITH REAL WEIGHTS: ANALOG COMPUTATIONAL COMPLEXITY Hava T. Siegelmann Department of Computer Science Rutgers University, New Brunswick, NJ 08903 E-mail: siegelma@yoko.rutgers.edu Eduardo D. Sontag Department of Mathematics Rutgers University, New Brunswick, NJ 08903
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rosenberg.scintigrams.ps.Z, 19921102 y y 201 Abstract 1 Introduction Neural Computation crr@cogsci.psych.utah.edu Charles Rosenberg, Ph.D. Jacob Erel, M.D. Henri Atlan, M.D., PhD. June, 1992 A Neural Network that Learns to Interpret Myocardial Planar Thallium Scintigrams This paper is to appear in . Supported by grants from the Ministry of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schmidhuber.selfref.ps.Z, 19921112 STEPS TOWARDS `SELF-REFERENTIAL' NEURAL LEARNING: A THOUGHT EXPERIMENT Technical Report CU-CS-627-92 J urgen Schmidhuber Department of Computer Science University of Colorado Campus Box 430, Boulder, CO 80309 November 11, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schmidhuber.predclass.ps.Z, 19921112 DISCOVERING PREDICTABLE CLASSIFICATIONS Technical Report CU-CS-626-92 J urgen Schmidhuber Department of Computer Science University of Colorado Campus Box 430, Boulder, CO 80309, USA yirgan@cs.colorado.edu Daniel Prelinger Institut f ur Informatik Technische Universit at M unchen Arcisstr. 21, 8000 M
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schmidhuber.subgoals.ps.Z, 19921112 PLANNING SIMPLE TRAJECTORIES USING NEURAL SUBGOAL GENERATORS Accepted by the Second International Conference on Simulations of Adaptive Behavior (SAB92), 1992 J urgen Schmidhuber Department of Computer Science University of Colorado Campus Box 430 Boulder, CO 80309, USA email: yirgan@cs.colorado.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/weigend.hkp-review.ps.Z, 19921124 To appear in ARTIFICIAL INTELLIGENCE (1993) (Elsevier Science Publishers) Book Review John A. Hertz, Anders S. Krogh, and Richard G. Palmer, Introduction to the Theory of Neural Computation 1 Reviewed by: 2 Andreas S. Weigend Xerox PARC 3333 Coyote Hill Road Palo Alto, CA 94304 (Received June 1992;
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/orponen.hoppow.ps.Z, 19921124 On the Computational Power of Discrete Hopfield Nets Pekka Orponen Department of Computer Science, University of Helsinki Teollisuuskatu 23, SF{00510 Helsinki, Finland E-mail: orponen@cs.helsinki.fi
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/floreen.attrrad.ps.Z, 19921124 Attraction radii in binary Hopfield nets are hard to compute Patrik Flor een Pekka Orponen Department of Computer Science, University of Helsinki SF{00510 Helsinki, Finland
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/orponen.nncomp.ps.Z, 19921124 Neural Networks and Complexity Theory Pekka Orponen Department of Computer Science, University of Helsinki Teollisuuskatu 23, SF{00510 Helsinki, Finland E-mail: orponen@cs.helsinki.fi
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR31.ps.gz, 19921125 owar a niversal ra ewor for ata ranslation John A. Gawkowski Information Dimensions Inc. 5080 Tuttle Crossing Blvd. Dublin, Oh. 43017 email: gawkowski@idicl1.idi.battelle.org phone: (614) 761-7436 S. A. Mamrak Department of Computer and Information Science The Ohio State University November 23, 1992 S
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rosen.advsim.ps.Z, 19921130 Function Optimization based on Advanced Simulated Annealing1 Bruce Rosen Division of Mathematics, Computer Science and Statistics The University of Texas at San Antonio, San Antonio, Texas, 78249
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR35.ps.gz, 19921204 e or s hypercube, graph embedding, binary trees, meshes, regular binaryreflected trees, congestion, dilation. This research was s pported ationa cience o ndation nder rant - . 1 ntro uction The embedding of a guest graph G into a host graph consists of two functions: an f : (G) ! ( ) mapping the vertex
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ohlsson.track.ps.Z, 19921204 December 1992 LU TP 92-28 Extensions and Explorations of the Elastic Arms Algorithm Mattias Ohlsson1 Department of Theoretical Physics, University of Lund S olvegatan 14A, S-22362 Lund, Sweden (Submitted to Computer Physics Communications)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR24.ps.gz, 19921204 Design and Specification of Iterators Using the Swapping Paradigm Bruce W. Weide1 Stephen H. Edwards1 Douglas E. Harms2 David A. Lamb3 Abstract How should iterators be abstracted and encapsulated in modern imperative languages, e.g., Ada and C++ We consider the combined impact of several factors on this
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/flower.swnp.ps.Z, 19921221 FIGURE 4: Comparison of the number of Feedforward passes performed to achieve convergence on a range of problems using SWNP and WP. 4 CONCLUSION The algorithm presented, SWNP, performs gradient descent on the weight space of an ANN, using a finite difference to approximate the gradient. The method is
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/arnoldi.sc-transform.ps.Z, 19921221 Authorization to lend and reproduce this thesis As the sole author of this thesis, I authorize Brown university to lend it to other institutions or individuals for the purpose of scholarly research. Hans-Martin Rudolf Arnoldi (Date) I further authorize Brown University to reproduce this thesis by
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/klagges.rndwired-cascor.ps.Z, 19921221 Limited Fan-in Random Wired Cascade-Correlation Henrik Klagges and Michael Soegtrop IBM Research Division Physics Group Munich Schellingstrasse 4/III D{8000 Muenchen 40 Federal Republic of Germany E-mail: henrik@robots.ox.ac.uk, uh311ae@sun1.lrz-muenchen.de
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schiff.gann.ps.Z, 19921221 Synthesis and Performance Analysis of Multilayer Neural Network Architectures W. Schiffmann, M. Joost, R. Werner University of Koblenz Institute f ur Physics Rheinau 3{4 D-5400 Koblenz e-mail: schiff@infko.uni-koblenz.de Technical Report 16/1992 Contents 1 Introduction 3 2 Genetic Algorithms 4 2.1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/burgess.hipnav.ps.Z, 19921222 4 Performance The model achieves latent learning (i.e. the map is constructed independently of knowledge of the goal, see e.g. Tolman, 1948). A piece of food encountered only once, after exploration, can be returned to, see Fig. 5c. Notice that a large part of the environment was never visited during
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/burgess.gencon.ps.Z, 19921222 International Journal of Neural Systems, Vol. 3, (Supp. 1992) 000{000 Proceedings of the Neural Networks from Biology to High Energy Physics Workshop c World Scientific Publishing Company THE GENERALIZATION OF A CONSTRUCTIVE ALGORITHM IN PATTERN CLASSIFICATION PROBLEMS Neil Burgess, Department of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/blackmore.incremental.ps.Z, 19921224 ABCDEFGHIJKMNOPQRYZWLTUVXS123456 (a) BCDEFGAIJHKLMSNOPTUVQRWXYZ123564 (b) Figure 6: Feature map representation for the spanning tree data. (a) Map derived by the standard self-organizing algorithm (Kohonen 1990). The map is hexagonally connected. The spanning tree structure is clearly present in the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/leow.visual-schemas.ps.Z, 19921224 Representing Visual Schemas in Neural Networks for Object Recognition Wee Kheng Leow and Risto Miikkulainen Technical Report AI92-190 Department of Computer Sciences, University of Texas at Austin, Austin, Texas 78712, USA leow@cs.utexas.edu, risto@cs.utexas.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nowlan.vismotion.ps.Z, 19930105 Filter Selection Model for Generating Visual Motion Signals Steven J. Nowlan CNL, The Salk Institute P.O. Box 85800, San Diego, CA 92186-5800 Terrence J. Sejnowski CNL, The Salk Institute P.O. Box 85800, San Diego, CA 92186-5800
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/baldi.compbiohmm.ps.Z, 19930107 10 20 30 40 50 60 70 80 90 100 110 120 130 140 0.0 1.0 2.0 3.0 Main State Entropy Values 150 160 170 180 190 200 210 220 230 240 250 260 270 280 0.0 1.0 2.0 3.0 0.0 0.5 1.0 1.5 2.0 2.5 3.0 10 30 50 Entropy Distribution Figure 4: Kinase emission entropy plot and distribution. Fragments. Journal of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pluto.nips92.ps.Z, 19930113 Learning Mackey-Glass from 25 examples, Plus or Minus 2 Mark Plutowski* Garrison Cottrell* Halbert White** Institute for Neural Computation Department of Computer Science and Engineering *Department of Economics University of California, San Diego La Jolla, CA 92093
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rohwer.howmany.ps.Z, 19930113 How many thoughts can you think Richard Rohwer Dept. of Computer Science and Applied Mathematics Aston University, Birmingham B4 7ET, UK 20 November 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.vague.ps.Z, 19930113 INDE TERMS: artificial intelligence, knowledge-based systems, neural networks, reasoning, knowledge representation, vagueness s er, e r se e r s r r e e e s s ere s r s r e s e ere es. e e s s s e e s, e s ere e e r es re rese e s s re rese r es e e s, e er s r e re se re e rs e e . se e er e ee e e es
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mcrae.corredprops.ps.Z, 19930115 The Role of Correlated Properties in Accessing Conceptual Memory Ken McRae Virginia de Sa University of Rochester, Rochester, NY Mark S. Seidenberg University of Southern California, Los Angeles, CA keywords: correlated properties, conceptual memory, word meaning, connectionist models, semantic priming
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cohn.robot-learning-summary.ps, 19930119 ROBOT LEARNING Summary of the post-NIPS workshop Vail, Colorado, Dec 5th, 1992 David A. Cohn (MIT) Tom Mitchell (CMU) Sebastian Thrun (CMU) cohn@psyche.mit.edu mitchell@cs.cmu.edu thrun@cs.cmu.edu Robot learning has grasped the attention of many researchers over the past few years. Previous robotics
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.bpsic.fig1.ps.Z, 19930119 KOLEN & POLLACK Figure 2 : Schematic Network 1 5 7 8 2 4 3 6 9 Figure 3 : (-5-3+3+6Y-1-6+7X) h=3.25 a=0.40 Figure 4 : (+4-7+6+0-3Y+1X+1) h=2.75 a=0.00 Figure 5 : (-5+5+1-6+3XY+8+3) h=2.75 a=0.80 Figure 6 : (YX-3+6+8+3+1+7-3) h=3.25 a=0.00 Figure 7 : (Y+3-9-2+6+7-3X+7) h=3.25 a=0.60
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/klagges.massively-parallel.ps.Z, 19930119 A Massively Parallel Neurocomputer Michael Soegtrop and Henrik Klagges IBM Research Division Physics Group Munich Schellingstrasse 4/III D{8000 Muenchen 40 Federal Republic of Germany E-mail: henrik@robots.ox.ac.uk, uh311ae@sun1.lrz-muenchen.de
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lazzaro.audnerve.ps.Z, 19930119 Temporal Adaptation in a Silicon Auditory Nerve John Lazzaro CS Division UC Berkeley 571 Evans Hall Berkeley, CA 94720
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.robots-icnn93.ps.Z, 19930119 Exploration and Model Building in Mobile Robot Domains Sebastian B. Thrun 1 University of Bonn, Institut f ur Informatik III R omerstr. 164, D-5300 Bonn 1, Germany E-mail: thrun@uran.informatik.uni-bonn.de To appear in: Proceedings of the IEEE International Conference on Neural Networks San Francisco,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mitchell.ebnn-nips5.ps.Z, 19930119 To appear in: Advances in Neural Information Processing Systems 5 C.L. Giles, S.J. Hanson, and J.D. Cowan (eds.) Morgan Kaufmann, San Mateo, CA, 1992 Explanation-Based Neural Network Learning for Robot Control Tom M. Mitchell School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yang.cascor.ps.Z, 19930119 Experiments with the Cascade-Correlation Algorithm Jihoon Yang and Vasant Honavar Technical Report # 91-16 July 1991; Revised August 1991 Department of Computer Science 226 Atanasoff Hall Iowa State University Ames, IA 50011-1040, U.S.A. Experiments with the Cascade-Correlation Algorithm Jihoon Yang &
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rognvaldsson.lvq-mlp.ps.Z, 19930119 LU TP 92-18 June 1992 Pattern Discrimination Using Feed-Forward Networks - a Benchmark Study of Scaling Behaviour Thorsteinn R ognvaldsson1 Department of Theoretical Physics, University of Lund, S olvegatan 14 A, S-223 62 Lund, Sweden Submitted to Neural Computation
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thgoh.sense.ps.Z, 19930119 Semantic Extraction Using Neural Network Modelling and Sensitivity Analysis TH Goh, Francis Wong Institute of Systems Science National University of Singapore Heng Mui Keng Terrace, Kent Ridge Singapore 0511 Email: ISSGTH@NUSVM.BITNET thgoh@iss.nus.sg
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bradtke.nips5.ps.Z, 19930121 Reinforcement Learning Applied to Linear Quadratic Regulation Steven J. Bradtke Computer Science Department University of Massachusetts Amherst, MA 01003 bradtke@cs.umass.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/barto.realtime-dp.ps.Z, 19930121 Learning to Act using Real-Time Dynamic Programming Andrew G. Barto Steven J. Bradtke Satinder P. Singh Department of Computer Science University of Massachusetts, Amherst MA 01003 January 12, 1993 Submitted to AI Journal special issue on Computational Theories of Interaction and Agency The authors
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plate.nips5.ps.Z, 19930121 To appear in C. L. Giles, S. J. Hanson, and J. D. Cowan, editors, Advances in Neural Information Processing Systems 5 (NIPS*92), Morgan Kaufmann, San Mateo, CA Holographic Recurrent Networks Tony A. Plate Department of Computer Science University of Toronto Toronto, M5S 1A4 Canada
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ahmad.missing.ps.Z, 19930122 Some Solutions to the Missing Feature Problem in Vision
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schuetze.wordspace.ps.Z, 19930122 Word Space Hinrich Sch utze Center for the Study of Language and Information Ventura Hall Stanford, CA 94305-4115
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cauwenberghs.nips92.ps.Z, 19930125 A Fast Stochastic Error-Descent Algorithm for Supervised Learning and Optimization Gert Cauwenberghs California Institute of Technology Mail-Code 128-95 Pasadena, CA 91125 E-mail: gert@cco.caltech.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wahba.ssanova.ps.Z, 19930127 Smoothing Spline ANOVA with Component-Wise Bayesian Confidence Intervals" To Appear, J. Computational and Graphical Statistics CHONG GU and GRACE WAHBA November 11, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wahba.soft-class.ps.Z, 19930127 Soft Classification, a. k. a. Risk Estimation, via Penalized Log Likelihood and Smoothing Spline Analysis of Variance Grace Wahba, Chong Gu, Yuedong Wang and Richard Chappell January 20, 1993 University of Wisconsin, Madison Statistics Dept TR 899
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nolfi.self-sel.ps.Z, 19930128 Self-selection of Input Stimuli for Improving Performance Stefano Nolfi Domenico Parisi Institute of Psychology, CNR V.le Marx 15, 00137 Rome - Italy E-mail: stiva@irmkant.Bitnet domenico@irmkant.Bitnet
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sbcho.nn_architects.ps.Z, 19930201 Feedforward Neural Network Architectures for Complex Classification Problems Sung-Bae Choy and Jin H. Kim Center for Artificial Intelligence Research and Computer Science Department Korea Advanced Institute of Science and Technology 373-1, Koosung-dong, Yoosung-ku, Taejeon 305-701, Republic of Korea
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tresp.rules.ps.Z, 19930201 To appear in: C. L. Giles, S. J. Hanson, and J. D. Cowan, eds., Advances in Neural Information Processing Systems 5, San Mateo, CA, Morgan Kaufman, 1993. Network Structuring And Training Using Rule-based Knowledge Volker Tresp Siemens AG Central Research Otto-Hahn-Ring 6 8000 M unchen 83, Germany
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR32.ps.gz, 19930202 eywords: Computational Complexity, Probabilistic classes, Polynomial-time hierarchy ntr ucti n Toda and Ogiwara showed that PH d BP C=P; that is, the polynomial-time hierarchy is contained in C=P with arbitrarily low double-sided error probability. Tarui independently proved and improved
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bodenhausen.architectural_learning.ps.Z, 19930204 5. SUMMARY AND CONCLUSIONS The results on three different tasks show that the ASO algorithm can achieve equal or better results than handtuned architectures without any tuning to the particular task. Table 3 shows that the MSTDNN network optimized by ASO can adapt to different amounts of training data.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bodenhausen.application_oriented.ps.Z, 19930204 TABLE 1. Speech Recognition Performances (Alphabet Recognition) training testing manually optimized MSTDNN architecture with DTW 94.3% 85.0% manually optimized MSTDNN with gaussian smoothing of the DTW path 98.9% 88.0% automatically optimized MSTDNN architecture with standard DTW 97.1% 85.0%
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR07.ps.gz, 19930208 StEP(3D): A PORTABLE DISCOUNT USABILITY EVALUATION PLAN FOR 3D INTERACTION Scott B. Grissom Gary Perlman Bolz Hall 228 Department of Computer and Information Science The Ohio State University Columbus, OH 43210 grissom@cis.ohio-state.edu perlman@cis.ohio-state.edu Few interfaces of 3D systems have been
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rohwer.howmany.usa.ps.Z, 19930208 How many thoughts can you think Richard Rohwer Dept. of Computer Science and Applied Mathematics Aston University, Birmingham B4 7ET, UK 20 November 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rohwer.reprep.ps.Z, 19930208 A representation of representation applied to a discussion of variable binding Richard Rohwer Dept. of Computer Science and Applied Mathematics Aston University, Birmingham B4 7ET, UK 26 August 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mcrae.pretrained.ps.Z, 19930209 Catastrophic Interference is Eliminated in Pretrained Networks Ken McRae, University of Rochester and Phil A. Hetherington, McGill University When modeling strictly sequential experimental memory tasks, such as serial list learning, connectionist networks appear to experience excessive retroactive
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mozer.architectures.ps.Z, 19930209 To appear in: A. Weigend & N. Gershenfeld (Eds.), Predicting the future and understanding the past. Redwood City, CA: Addison-Wesley Publishing. Neural net architectures for temporal sequence processing Michael C. Mozer Department of Computer Science & Institute of Cognitive Science University of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/martin.unsmearing.ps.Z, 19930210 In press; to appear in S.J. Hanson, J.D. Cowan, & C.L. Giles, Eds., Advances in Neural Information Processing Systems, 5. San Mateo, CA: Morgan Kaufmann Publishers, 1993. Unsmearing Visual Motion: Development of Long-Range Horizontal Intrinsic Connections Kevin E. Martin Jonathan A. Marshall Department
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/neal.em.ps.Z, 19930216 A New View of the EM Algorithm that Justifies Incremental and Other Variants Radford M. Neal and Geoffrey E. Hinton Department of Computer Science University of Toronto 10 King's College Road Toronto, Canada M5S 1A4 12 February 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hofstadter.letter-spirit.ps.Z, 19930216 Letter Spirit: An Emergent Model of the Perception and Creation of Alphabetic Style Douglas Hofstadter & Gary McGraw Indiana University Center for Research on Concepts and Cognition Department of Computer Science 510 North Fess Street Bloomington, Indiana 47405 dughof@cogsci.indiana.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/demers.nips92-robot.ps.Z, 19930217 Global Regularization of Inverse Kinematics for Redundant Manipulators David DeMers Dept. of Computer Science & Engr. Institute for Neural Computation University of California, San Diego La Jolla, CA 92093-0114 Kenneth Kreutz-Delgado Dept. of Electrical & Computer Engr. Institute for Neural Computation
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/demers.nips92-nldr.ps.Z, 19930217 Non Linear Dimensionality Reduction David DeMers & Garrison Cottrelly Dept. of Computer Science & Engr., 0114 Institute for Neural Computation University of California, San Diego 9500 Gilman Dr. La Jolla, CA, 92093-0114
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/georgiou.perceptrons.ps.Z, 19930219 The Multivalued and Continuous Perceptrons George M. Georgiou Computer Science Department California State University San Bernardino, CA 92407 E-mail: georgiou@wiley.csusb.edu January, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/vaario.evolution.ps.Z, 19930226 Toward Evolutionary Design of Autonomous Systems Jari Vaario Koichi Hori Setsuo Ohsuga The University of Tokyo Research Center for Advanced Science and Technology Komaba 4-6-1, Meguro-ku, 153 Tokyo, Japan Phone: +81-3-3481-4486, FAX: +81-3-3481-4585 E-mail: jari@ai.rcast.u-tokyo.ac.jp Original
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mel.memory.ps.Z, 19930226 emor a acit of an citable endritic ree artlett el Previous comparmental modeling studies have shown that the dendritic trees of neocortical pyramidal cells may be cluster-sensitive", i.e. selectively responsive to spatially clustered, rather than diffuse, patterns of synaptic activation. The local
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/vangelder.kamasutra.ps.Z, 19930226 van Gelder and Port 1 February 23 , 1993 Beyond Symbolic: Prolegomena to a Kama-Sutra of Compositionality1 Timothy van Gelder2 and Robert Port3 Cognitive Science Program Indiana University Bloomington, Indiana, 47405 tgelder@indiana.edu, port@indiana.edu Consider some of the obvious differences between
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/vaario.emergent.ps.Z, 19930226 An Emergent Construction of Adaptive Neural Architectures Jari Vaario Setsuo Ohsuga The University of Tokyo Research Center for Advanced Science and Technology Komaba 4-6-1, Meguro-ku, 153 Tokyo, Japan E-mail: jari@ohsuga.rcast.u-tokyo.ac.jp
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tsung.phase.ps.Z, 19930302 Phase-Space learning for recurrent networks Fu-Sheng Tsung and Garrison W Cottrell Department of Computer Science & Engineering and Institute for Neural Computation University of California, San Diego, USA February 17, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/doya.bifurcation.ps.Z, 19930303 1 BIFURCATIONS IN THE LEARNING OF RECURRENT NEURAL NETWORKS Kenji Doya doya@crayfish.ucsd.edu Department of Biology University of California, San Diego La Jolla, CA 92093-0322, USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/doya.synchronization.ps.Z, 19930303 Adaptive Synchronization of Neural and Physical Oscillators Kenji Doya University of California, San Diego La Jolla, CA 92093-0322, USA Shuji Yoshizawa University of Tokyo Bunkyo-ku, Tokyo 113, Japan
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/doya.universality.ps.Z, 19930303 Universality of Fully-Connected Recurrent Neural Networks Kenji Doya doya@crayfish.ucsd.edu Department of Biology University of California, San Diego La Jolla, CA 92093-0322, USA February 1, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/doya.dimension.ps.Z, 19930303 Dimension Reduction of Biological Neuron Models by Artificial Neural Networks Kenji Doya and Allen I. Selverston doya@crayfish.ucsd.edu Department of Biology University of California, San Diego La Jolla, CA 92093-0322, USA December 28, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dayan.tdl.ps.Z, 19930303 TD(>=) Converges with Probability 1 Peter Dayan Terrence J Sejnowski dayan@helmholtz.sdsc.edu tsejnowski@ucsd.edu CNL, The Salk Institute PO Box 85800, San Diego, CA 92186-5800. Running head: TD(>=) Converges with Probability 1 Keywords: reinforcement learning, temporal differences, Q-learning
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/doya.bifurcation2.ps.Z, 19930303 Bifurcations of Recurrent Neural Networks in Gradient Descent Learning Kenji Doya doya@crayfish.ucsd.edu Department of Biology University of California, San Diego La Jolla, CA 92093-0322, USA February 1, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/das.prior_knowledge.ps.Z, 19930305 Using Prior Knowledge in an NNPDA to Learn Context-Free Languages Sreerupa Das Dept. of Comp. Sc. & Inst. of Cognitive Sc. University of Colorado Boulder, CO 80309 C. Lee Giles* NEC Research Inst. 4 Independence Way Princeton, NJ 08540 Guo-Zheng Sun Inst. for Adv. Comp. Studies University of Maryland
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sontag.uniqueness.ps.Z, 19930308 UNIQUENESS OF WEIGHTS FOR NEURAL NETWORKS Francesca Albertini and Eduardo D. Sontagy Department of Mathematics Rutgers University, New Brunswick, NJ 08903 Vincent Maillotz D epartement de Math ematiques et d'Informatique Ecole Normale Sup erieure, 75005 Paris 1 Introduction In most applications dealing
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sontag.vc.ps.Z, 19930308 An example is furnished by f(x) = cos(x), and ff = 1 1+x2 . This shows that arbitrary (not exp-ra definable) analytic functions may result in architectures with infinite VC dimension. (Moreover, the architecture used is the simplest one that appears in neural nets practice.) Note that if we wish the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gullapalli.uncertainty-nips5.ps.Z, 19930309 Learning Control Under Extreme Uncertainty Vijaykumar Gullapalli Computer Science Department University of Massachusetts Amherst, MA 01003
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR03.ps.gz, 19930309 tr ct n t is a er, e consi er t e sin e source an u ti source u ticastin ro e in or o e route net or s. e ro ose a enera trip a e o el or an net or t at as at east virtua c anne s er sica c anne . e un er in conce t is a no e se uence ca e irt a e trip, ic a a s e ists in ra s o an to o o . sin suc a se
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.nips92.ps.Z, 19930309 On the Use of Evidence in Neural Networks David H. Wolpert The Santa Fe Institute 1660 Old Pecos Trail Santa Fe, NM 87501
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/day.temporal.ps.Z, 19930309 Preprint: Continuous-Time Temporal Back-Propagation with Adaptable Time Delays1 Shawn P. Day2 Michael R. Davenport3 August 1991 Revised: April 1992 To appear in: IEEE Transactions on Neural Networks
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.ex_learning.ps.Z, 19930311 AN INVESTIGATION OF EXHAUSTIVE LEARNING by David H. Wolpert, Alan Lapedes* * - Theoretical Division and Center for Non-linear Studies, Los Alamos National Laboratory, Los Alamos, NM, 87545. Currently at The Santa Fe Institute, 1660 Old Pecos Trail, Suite A, Santa Fe, NM, 87501. (dhw@santafe.edu) ** -
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kirk.nips92.ps.Z, 19930312 Analog VLSI Implementation of Multi-dimensional Gradient Descent David B. Kirk, Douglas Kerns, Kurt Fleischer, Alan H. Barr California Institute of Technology Beckman Institute 350-74 Pasadena, CA 91125 E-mail: dk@egg.gg.caltech.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kambhatla.nonlinear.ps.Z, 19930312 Fast Non-Linear Dimension Reduction Nandakishore Kambhatla and Todd K. Leen Department of Computer Science and Engineering Oregon Graduate Institute of Science and Technology 19600 N.W. von Neumann Drive, Beaverton OR 97006-1999
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kirk.nips91.ps.Z, 19930315 Constrained Optimization Applied to the Parameter Setting Problem for Analog Circuits David Kirk, Kurt Fleischer, Lloyd Watts , Alan Barr Computer Graphics 350-74 California Institute of Technology Pasadena, CA 91125
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1991/TR6.ps.gz, 19930316 1 A stract Based on the and -classes of the polynomial-time hierarchy, Sch oning introduced low and high hierarchies within NP. Several classes of sets have been located in the bottom few levels of these hierarchies . Most results placing sets in the
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1991/TR22.ps.gz, 19930316 The Extended Low Hierarchy Is an Infinite Hierarchy 1 Ming-Jye Sheu Timothy J. Long Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 October 20, 1992 1This work was supported in part by NSF Grant CCR-8909071
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR09.ps.gz, 19930316 UP and the Low and High Hierarchies: A Relativized Separation 1 Ming-Jye Sheu and Timothy J. Long sheu-m@cis.ohio-state.edu, long@cis.ohio-state.edu Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 January 10, 1993 1This work was supported in part by NSF
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/buntine.second.ps.Z, 19930317 Computing Second Derivatives in Feed-Forward Networks: a Review Wray L. Buntine RIACS & NASA Ames Research Center Mail Stop 269{2 Moffet Field, CA 94035{1000, USA wray@kronos.arc.nasa.gov Andreas S. Weigend Xerox PARC 3333 Coyote Hill Road Palo Alto, CA 94304, USA weigend@cs.colorado.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/georg.nips92.ps.Z, 19930318 The Power of Approximating: a Comparison of Activation Functions Bhaskar DasGupta Department of Computer Science University of Minnesota Minneapolis, MN 55455-0159 email: dasgupta@cs.umn.edu Georg Schnitger Department of Computer Science The Pennsylvania State University University Park, PA 16802 email:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mareschal.seriate.ps.Z, 19930319 Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society 1993. Hillsdale, NJ: Erlbaum. A Connectionist Model of the Development of Seriation Denis Mareschal Thomas R. Shultz Department of Experimental Psychology Department of Psychology University of Oxford McGill University South
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR09.ps.gz, 19930323 Using Logging and Asynchronous Checkpointing to Implement Recoverable Distributed Shared Memory Golden G. Richard III Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 Email: {grichard, singhal}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.overfitting.ps.Z, 19930323 ON OVERFITTING AVOIDANCE AS BIAS by David H. Wolpert The Santa Fe Institute, 1660 Old Pecos Trail, Suite A, Santa Fe, NM, 87501, dhw@santafe.edu SFI TR 92-03-5001
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/reilly.eyemove.ps.Z, 19930324 To appear in Proceedings of the 15th Annual Meeting of the Cognitive Science Society, Boulder, CO. A Connectionist Attentional Shift Model of Eye-Movement Control in Reading Ronan Reilly Department of Computer Science University College Dublin Belfield, Dublin 4, Ireland rreilly@ccvax.ucd.ie
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/reilly.boundary.ps.Z, 19930324 To appear in Proceedings of the 15th Annual Meeting of the Cognitive Science Society, Boulder, CO. Boundary effects in the linguistic representations of simple recurrent networks Ronan Reilly Department of Computer Science University College Dublin Belfield, Dublin 4, Ireland rreilly@ccvax.ucd.ie
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR34.ps.gz, 19930326 ey Words: distributed system, termination detection, fault-tolerance, reliability, fail-stop processor, weight-throwing. 1 n roduc ion In a distributed system, a set of processes cooperate and communicate with one another by message-passing. Each process switches between active and idle states. An
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/irina.explicit.ps.Z, 19930406 How to Explicit A Neural Network Trained to Predict Proteins Secondary Structure I.Tchoumatchenko, F. Vissotsky, J.-G. Ganascia1 ACASA, LAFORIA-CNRS, Universit e Paris-VI, 4 Place Jussieu, 75252 Paris, CEDEX 05 France tel: 33-1-44-27-70-09 fax: 33-1-44-27-70-00
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR15.ps.gz, 19930406 1 Voxel - Based Morphing Work in Progress Report Asish Law and Roni Yagel Department of Computer & Information Science The Ohio State University Phone: (614) 292-0060; Fax: (614) 292-2911 Email: {law, yagel}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hildebrandt.batch.ps.Z, 19930406 A Nonlinear Error Function on Which Per-Sample BP is Faster than Batch BP Thomas H. Hildebrandt Electrical Engineering and Computer Science Department Room 304 Packard Laboratory 19 Memorial Drive West Lehigh University Bethlehem, PA 18015-3084 thildebr@athos.eecs.lehigh.edu March 23, 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR14.ps.gz, 19930408 1 Efficient Feed-Forward Volume Rendering Techniques for Vector and Parallel Processors Raghu K. Machiraju and Roni Yagel Department of Computer and Information Science The Ohio State University 2036 Neil Ave. Columbus, OH 43210-1277 Phone: (614) 292-0060 Fax: (614) 292-2911 e-mail:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/touretzky.extra-figure.ps.Z, 19930409 5 10 15 20 spikes/sec 90 180 270 360 Head Direction (deg) MRL
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR10-DIR/TR10.fig.ps.gz, 19930409 (i,k) (i,j) (x,y,z) (x,y,z) (i,k ) (i,j ) (x,y,z) (x,y,z) Fig. 8 (a) (b) Fig. 1 Screen Volume (a) (e) (f) (b) (d) Fig. 7 Fig. 4 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shawetaylor.symdisc.ps.Z, 19930409 SYMMETRIES AND DISCRIMINABILITY IN FEEDFORWARD NETWORK ARCHITECTURES John Shawe-Taylor Department of Computer Science Royal Holloway and Bedford New College University of London December 10, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.lecture92.ps.Z, 19930409 To appear in 1992 Lectures in Complex Systems, L. Nadel and D. Stein (Eds.), Addison-Wesley, 1993 COMBINING GENERALIZERS USING PARTITIONS OF THE LEARNING SET by David H. Wolpert Santa Fe Institute, 1660 Old Pecos Trail, Suite A, Santa Fe, NM, 87501, USA, (dhw@santafe.edu)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR10-DIR/TR10.words.ps.gz, 19930409 Accelerating Volume Animation by Space-Leaping D Roni Yagel and Zhouhong Shi epartment of Computer and Information Science The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/touretzky.sinusoidal-arrays.ps.Z, 19930412 Neural Representation of Space Using Sinusoidal Arrays David S. Touretzky,1 A. David Redish, Hank S. Wan School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 March 1993 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 To appear in Neural Computation.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR21.ps.gz, 19930416 s s, - , s. -s . A stra t: A termination detector is a distributed algorithm that, when superimposed on a distributed system of n processes, is able to determine whether the computation of the underlying system has terminated. Fault tolerance is one of the most desirable properties of distributed
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR13.ps.gz, 19930419 s ey ords: Verification, Mutual exclusion algorithms, Distributed algorithms. 1 ntroduction A distributed system consists of a set of autonomous, geographically dispersed computers that are connected by a network. The computers do not share a common memory and communicate with one another exclusively by
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nolfi.growing.ps.Z, 19930421 Institute of Psychology C.N.R. - Rome Growing neural networks Stefano Nolfi Domenico Parisi Institute of Psychology National Research Council E-mail: stiva@irmkant.Bitnet domenico@irmkant.Bitnet December 1991 Technical Report PCIA-91-15 Department of Cognitive Processes and Artificial Intelligence 15,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR17.ps.gz, 19930421 alluri Es ar P. Sada appan .- . uang . is anat an
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/meeden.robot.ps.Z, 19930421 Emergent Control and Planning in an Autonomous Vehicle To appear in Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society Lisa Meedeny and Gary McGraw y and Douglas Blanky yDepartment of Computer Science Center for Research on Concepts and Cognition Indiana University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cummins.temporal-patterns.ps.Z, 19930423 Representation of Temporal Patterns in Recurrent Networks Fred Cumminsy Cognitive Science Program Indiana University Bloomington, IN 47405 fcummins@ucs.indiana.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zimmer.learning_surfaces.ps.Z, 19930423 ICANN 93, Amsterdam September 13-16 , 1993 SPIN Learning and Forgetting Surface Classifications with Dynamic Neural Networks Herman Keuchel, Ewald von Puttkamer & Uwe R. Zimmer University of Kaiserslautern - Computer Science Department - Research Group Prof. E. v. Puttkamer P.O. Box 3049 - W6750
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jordan.hierarchies.ps.Z, 19930427 Hierarchical mixtures of experts and the EM algorithm Michael I. Jordan Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Robert A. Jacobs Department of Psychology University of Rochester MIT Computational Cognitive Science Technical Report 9301 April 26, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.nn-sp-bib.ps.Z, 19930428 xxiv Eckmiller, R., Hartmann, G., and Hauske, G., eds, Parallel Processing in Neural Systems and Computers, pages 49902. Elsevier. T. Van Gelder, (1989). Compositionality and the explanation of cognitive processes," Proceedings of the Annual Conference of the Cognitive Science Society, pp.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/boers.biological-metaphors.ps.Z, 19930428 Biological metaphors and the design of modular artificial neural networks Master's thesis of Egbert J.W. Boers and Herman Kuiper Departments of Computer Science and Experimental and Theoretical Psychology at Leiden University, the Netherlands Preface This thesis is the result of a research done at the
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR20.ps.gz, 19930505 A distributed system is characteri ed by the lack of a global time. Many models of logical time have been proposed in the past to solve this problem. Logical clocks have been developed to deduce causality and potential causality between events in a distributed computation. These clocks are unbounded and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hwang.bplppl.ps.Z, 19930505 Regression Modeling in Back-Propagation and Projection Pursuit Learning Jenq-Neng Hwangy, Shyh-Rong Layy, Martin Maechlerz, Doug Martin , Jim Schimert This research was partially supported through grants from the National Science Foundation under Grant No. ECS-9014243, and from Office of Naval Research
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hwang.nnmrf.ps.Z, 19930505 Textured Image Synthesis and Segmentation via Neural Network Probabilistic Modeling Jenq-Neng Hwang, Eric Tsung-Yen Chen Information Processing Laboratory Department of Electrical Engineering, FT-10 University of Washington Seattle, WA 98195
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR19.ps.gz, 19930505 Logical clocks and vector clocks have been proposed in the past to capture causality and potential causality between events in a distributed computation. These clocks associate timestamps with events such that the ordering between timestamps captures the causality or potential causality between events.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hwang.srnn.ps.Z, 19930505 Mental Image Transformation and Matching using Surface Reconstruction Neural Networks Jenq-Neng Hwang, Yen-Hao Tseng Information Processing Laboratory Department of Electrical Engineering, FT-10 University of Washington Seattle, WA 98195
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fritzke.icann93.ps.Z, 19930507 To appear in: ICANN '93: Proceedings of the International Conference on Artificial Neural Networks, Amsterdam, The Netherlands, September 13-16, 1993 Vector Quantization with a Growing and Splitting Elastic Net Bernd Fritzke International Computer Science Institute 1947 Center Street, Suite 600
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fritzke.tr93-26.ps.Z, 19930507 INTERNATIONAL COMPUTER SCIENCE INSTITUTE I 1947 Center Street ffl Suite 600 ffl Berkeley, California 94704 ffl 1-510-642-4274 ffl FAX 1-510-643-7684 Growing Cell Structures { A Self-organizing Network for Unsupervised and Supervised Learning Bernd Fritzkey TR-93-026 May 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lister.anneal.ps.Z, 19930507 IEEE Int. Conf. on Neural Networks, San Francisco, March 1993, Vol. I pp 257-262. Annealing Networks and Fractal Landscapes Raymond Lister Dept. of Electrical Engineering, University of Queensland, QLD 4072, Australia
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fritzke.nips92.ps.Z, 19930507 To appear in: Advances in Neural Information Processing Systems 5 C.L. Giles, S.J Hanson, and J.D. Cowan (eds.) Morgan Kaufmann, San Mateo, CA, 1993 Kohonen Feature Maps and Growing Cell Structures { a Performance Comparison Bernd Fritzke International Computer Science Institute 1947 Center Street,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stiber.dynlearn.ps.Z, 19930518 Learning In Neural Models With Complex Dynamics Michael Stiber Department of Computer Science The Hong Kong University of Science and Technology Clear Water Bay, Kowloon Hong Kong email: stiber@cs.ust.hk Jos e P. Segundo Department of Anatomy and Cell Biology and Brain Research Institute University of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fontaine.wordrec.ps.Z, 19930521 Recognizing Handprinted Digit Strings: a Hybrid Connectionist/Procedural Approach Thomas Fontaine and Lokendra Shastri Computer and Information Science Department University of Pennsylvania Philadelphia, PA 19104-6389
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1992/TR26.ps.gz, 19930521 Optimal Evaluation of Fortran-90 Array Expressions for Distributed Memory Machines S.D. Kaushik, S.K.S. Gupta, C.-H. Huang, P. Sadayappan Department of Computer and Information Science The Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tesauro.tdgammon.ps.Z, 19930524 TD-Gammon, A Self-Teaching Backgammon Program, Achieves Master-Level Play Gerald Tesauro IBM Thomas J. Watson Research Center P. O. Box 704 Yorktown Heights, NY 10598 (tesauro@watson.ibm.com)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR21.ps.gz, 19930528 Performance of distributed computation have traditionally been characterized by measures based on number of messages exchanged, total information exchanged by messages, or the total execution time of the computation. Though important, these measures do not completely characterize a distributed
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR22.ps.gz, 19930528 Flush channels have been proposed as an alternative to FIFO and non-FIFO models of communication and have been found useful in a variety of applications. Flush channels while retaining the elegance and ease of program development in a FIFO environment provide higher communication level concurrency.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pet.delta.ps.Z, 19930528 March 1993 LU TP 93-4 Finding the Embedding Dimension and Variable Dependences in Time Series Hong Pi1 and Carsten Peterson2 Department of Theoretical Physics, University of Lund S olvegatan 14A, S-223 62 Lund, Sweden Submitted to Neural Computation
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thodberg.ace-of-bayes.ps.Z, 19930528 Ace of Bayes: Application of Neural Networks with Pruning Hans Henrik Thodberg The Danish Meat Research Institute Maglegaardsvej 2, DK-4000 Roskilde e-mail thodberg@nn.meatre.dk Manuscript 1132E, May 19, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/crespo.regularization.ps.Z, 19930604 TESTS OF DIFFERENT REGULARIZATION TERMS IN SMALL NETWORKS Crespo, J.L. Mora, E. Applied Mathematics and Computer Science Department University of Cantabria Avda. Los Castros, s/n 39005 Santander Spain
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pearlmutter.hessian.ps.Z, 19930614 Fast Exact Multiplication by the Hessian Barak A. Pearlmutter Siemens Corporate Research 755 College Road East Princeton, NJ 08540 bap@learning.siemens.com June 9, 1993 To appear in Neural Computation
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/biehl.unsupervised.ps.Z, 19930616 An exactly solvable model of unsupervised learning Michael Biehl CONNECT, The Niels Bohr Institute Blegdamsvej 17, DK-2100 Copenhagen O, Denmark
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.super.ps.Z, 19930618 Neural Nets with Superlinear VC-Dimension Wolfgang Maass Institute for Theoretical Computer Science Technische Universitaet Graz Klosterwiesgasse 32/2 A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR23.ps.gz, 19930621 Task Assignment on Distributed-Memory Systems with Adaptive Wormhole Routing Vibha A. Dixit-Radiya and Dhabaleswar K. Panda Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 radiya-v@cis.ohio-state.edu, panda@cis.ohio-state.edu Tel: (614)-292-5199, FAX:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mcauley.noise.ps.Z, 19930622 Analysis of the Effects of Noise on a Model for the Neural Mechanism of Short-Term Active Memory J. Devin McAuley and Joseph Stampfli Department of Computer Science Depertment of Mathematics Indiana University Bloomington, Indiana 47505 June 10, 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR24.ps.gz, 19930625 C C , A stract Given an arbitrary set S of n-bit vectors, we construct a random set S0 S, with a constant probability, such that if S <> ;, then S0 has an odd number of elements. We improve bounds on several recent results in complexity theory by using our construction instead of Valiant and Vazirani's
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/oh.generalization.ps.Z, 19930629 Generalization in a two-layer neural network Kukjin Kang, Jong-Hoon Oh Department of Physics, Pohang Institute of Science and Technology, Pohang, Kyongbuk, Korea Chulan Kwon, Youngah Park Department of Physics, Myong Ji University, Yongin, Kyonggi, Korea (January 10, 1993)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.agnostic.ps.Z, 19930629 Agnostic PAC-Learning of Functions on Analog Neural Nets Wolfgang Maass* Institute for Theoretical Computer Science Technische Universitaet Graz Klosterwiesgasse 32/2 A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/white.c-hebb-2.ps.Z, 19930706 5 5 Summary and Conclusions This paper has introduced Competitive Hebbian Learning 2, and presented a couple simple demonstrations of its ability as an algorithm for unsupervised learning in artificial systems. The other claim made for CHL 2, that it represents a simplified model for learning in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tss.nips92.ps.Z, 19930709 Classification of Electroencephalogram using Artificial Neural Networks A C Tsoi, D S C So, A Sergejew** Department of Electrical Engineering *Department of Psychiatry University of Queensland St Lucia, Queensland 4072 Australia March 16, 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR26.ps.gz, 19930709 Resilient and Flexible Ring Embedding in an Injured Hypercube Yu-Chee Tseng and Ten-Hwang Lai Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 Tel: (614)292-5813, Fax: (614)292-9021 E-mail: ftseng, laig@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/beyer.teams.ps.Z, 19930714 Learning from Examples, Agent Teams and the Concept of Reflection Uwe Beyer Frank Smieja June 15, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dasdan.gen-unsup.ps.Z, 19930715 Genetic Synthesis of Unsupervised Learning Algorithms Ali DAS DAN and Kemal OFLAZER Department of Computer Engineering and Information Science Bilkent University 06533 Bilkent, Ankara, TURKEY Email : dasdan@bcc.bilkent.edu.tr
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/luttrell.bayes-selforg.ps.Z, 19930716 This paper was submitted to Neural Computation on 10th May 1993 A Bayesian Analysis of Self-Organising Maps Stephen P Luttrell Adaptive Systems Theory Section Defence Research Agency St Andrews Rd, Malvern, Worcestershire, WR14 3PS, United Kingdom luttrell@signal.dra.hmg.gb
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jaakkola.convergence.ps.Z, 19930720 Submitted to Neural Computation. On the Convergence of Stochastic Iterative Dynamic Programming Algorithms Tommi Jaakkola Michael I. Jordan Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Satinder P. Singh Department of Computer Science University of Massachusetts at
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rognvaldsson.langevin.ps.Z, 19930721 LU TP 93-13 June 1993 On Langevin Updating in Multilayer Perceptrons Thorsteinn R ognvaldsson1 Department of Theoretical Physics, University of Lund, S olvegatan 14 A, S-223 62 Lund, Sweden Submitted to Neural Computation
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/perrone.MSE-averaging.ps.Z, 19930729 When Networks Disagree: Ensemble Methods for Hybrid Neural Networks Michael P. Perrone and Leon N Cooper y Physics Department Neuroscience Department Institute for Brain and Neural Systems Box 1843, Brown University Providence, RI 02912 Email: mpp@cns.brown.edu October 27, 1992
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolf.mutual2.ps.Z, 19930729 LANL LA-UR 93-833 26 SFI TR-93-07-047 vector of constants , and where is the zero -vector. In writing , the , and depen- dence is assumed. The second component of the general CF may be nonzero (see App. G). However, for the moment there is no need to present the full definition of the CF s encompassing
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR28.ps.gz, 19930809 Scalable Architectures with k-ary n-cube cluster-c organization 1 Debashis Basak and Dhabaleswar K. Panda Department of Computer and Information Science Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199 Email: basak,panda@cis.ohio-state.edu August 5, 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR29.ps.gz, 19930809 Designing Scalable Systems with two-level k-ary n-cube Wormhole-routed Interconnections 1 Debashis Basak and Dhabaleswar K. Panda Department of Computer and Information Science Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email: basak,panda@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/baldi.smoothhmm.ps.Z, 19930810 1 Smooth On-Line Learning Algorithms for Hidden Markov Models Pierre Baldi * Jet Propulsion Laboratory California Institute of Technology Yves Chauvin # Net-ID, Inc. A simple learning algorithm for Hidden Markov Models (HMMs) is presented together with a number of variations. Unlike other classical
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bengio.general.ps.Z, 19930813 Generalization of a Parametric Learning Rule Samy Bengio Yoshua Bengio Jocelyn Cloutier Jan Gecsei Universit e de Montr eal, D epartement IRO Case Postale 6128, Succ. "A", Montr eal, QC, Canada, H3C 3J7 e-mail: bengio@iro.umontreal.ca
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR16.ps.gz, 19930813 Optimal Fully Adaptive Wormhole Routing for Meshes Loren Schwiebert and D. N. Jayasimha Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210{1277 Email: floren, jayasimg@cis.ohio-state.edu April 12, 1993 Revised: August 13, 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR02.ps.gz, 19930907 s rac his paper deals with barrier synchronization in distributed-memory multiprocessors. e propose new and synchronization primitives to implement synchronization between two and multiple processors, respectively. he rendezvous primitive can wor with either wormhole or circuit-switched routing. wo
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dorffner.nn-clinical.ps.Z, 19930908 1 On Using Feedforward Neural Networks for Clinical Diagnostic Tasks Georg Dorffner Austrian Research Institute for Artificial Intelligence Schottengasse 3 A-1010 Vienna, Austria Tel: +43 1 53532810, Fax: +43 1 5320652, email: georg@ai.univie.ac.at and Dept. of Medical Cybernetics and Artificial
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dorffner.csfn.ps.Z, 19930908 1 A Unified Framework for MLPs and RBFNs: Introducing Conic Section Function Networks Georg Dorffner Dept. of Medical Cybernetics and Artificial Intelligence University of Vienna and Austrian Research Institute for Artificial Intelligence georg@ai.univie.ac.at
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.field-comp.ps.Z, 19930908 A Computationally Universal Field Computer That is Purely Linear David H. Wolpert Bruce J. MacLennany DRAFT Not to be Reproduced or Generally Distributed September 1, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/williams.policy-iter.ps.Z, 19930916 Analysis of Some Incremental Variants of Policy Iteration: First Steps Toward Understanding Actor-Critic Learning Systems Ronald J. Williams College of Computer Science Northeastern University Boston, MA 02115 rjw@ccs.neu.edu and Leemon C. Baird, III Wright Laboratory Wright-Patterson Air Force Base, OH
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zimmer.spin-nfds.ps.Z, 19930916 ANZIIS 93, Perth Western Australia December 1-3, 1993 SPIN-NFDS Learning and Preset Knowledge for Surface Fusion - A Neural Fuzzy Decision System - J rg Bruske, Ewald von Puttkamer & Uwe R. Zimmer University of Kaiserslautern - Computer Science Department - Research Group Prof. E. v. Puttkamer P.O. Box
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/priel.2_layered_perc.ps.Z, 19930916 Computational Capabilities of Restricted Two Layered Perceptrons Avner Priel, Marcelo Blatt, Tal Grossman and Eytan Domany Electronics Department, The Weizmann Institute of Science, Rehovot 76100, Israel Ido Kanter Department of Physics, Bar Ilan University, 52900 Ramat Gan, Israel (September 2, 1993)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.reinforce-approximation.ps.Z, 19930921 To appear in: Proceedings of the Fourth Connectionist Models Summer School Lawrence Erlbaum Publisher, Hillsdale, NJ, Dec. 1993 Issues in Using Function Approximation for Reinforcement Learning Sebastian Thrun Anton Schwartz Institut f ur Informatik III Dept. of Computer Science Universit at Bonn
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/meir.compress.ps.Z, 19930924 Data Compression and Prediction in Neural Networks Ronny Meir Department of Electrical Engineering Technion Haifa 32000, Israel rmeir@ee.technion.ac.il Jose F. Fontanariy IFQSC - DFCM Universidade de S~ao Paulo 13560 S~ao Carlos SP, Brazil fontanari@uspfsc.ifqsc.usp.ansp.br
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/meir.learn.ps.Z, 19930924 Learning Algorithms, Input Distributions and Generalization Ronny Meir Department of Electrical Engineering Technion Haifa 32000, Israel rmeir@ee.technion.ac.il June 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bessiere.iros93.ps.Z, 19930924 Paper published in IEEE-IROS'93 conference Intelligent RObots and Systems Yokohama - JAPAN - 1993 THE "ARIADNE'S CLEW"1 ALGORITHM: GLOBAL PLANNING WITH LOCAL METHODS2 Pierre BESSI RE3, Juan-Manuel AHUACTZIN, El-Ghazali TALBI & Emmanuel MAZER CNRS4 IMAG Institute, LIFIA5 & LGI6 laboratories
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.rnifs.ps.Z, 19930928 produce increases in both the number of apparent IP states and the observed complexity class of the system . In other words, the recurrent network states are not IP states in of themselves; they require an appropriate context which can elevate them to IP-hood. This context consists of a set of input
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lallement.hybrid-cam.ps.Z, 19930928 An Abstract Machine for Implementing Connectionist and Hybrid Systems on Multi-processor Architectures Yannick Lallementy, Thierry Cornuz, St ephane Viallex lallemen@loria.fr cornu@di.epfl.ch steph@ese-metz.fr September 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR30.ps.gz, 19930929 Online Hard Real-Time Scheduling for Hypercube Multiprocessors Davender Babbar and Phillip Krueger Department of Computer and Information Science The Ohio State University Columbus, OH 43210 September 29, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wong.scale_space.ps.Z, 19930930 A Nonlinear Scale-Space Filter by Physical Computation Yiu-fai Wong Institute for Scientific Computing Research, L-426 Lawrence Livermore National Laboratory Livermore, CA 94551 E-mail: wong@redhook.llnl.gov, Tel: (510) 422-3777
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jordan.convergence.ps.Z, 19931004 Convergence results for the EM approach to mixtures of experts architectures Michael I. Jordan Lei Xu Department of Brain and Cognitive Sciences Massachusetts Institute of Technology MIT Computational Cognitive Science Technical Report 9303 September 3, 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR32.ps.gz, 19931005 Parallel Compacting Free Buddy Subcubes in a Hypercube Yu-Chee Tseng, Ten-Hwang Lai, and Young Man Kim Department of Computer and Information Science The Ohio State University Columbus, OH 43210 { 1277 Tel: 614-292-5813, Fax: 614-292-2911 Email: ftseng, laig@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hwang.cclppl.ps.Z, 19931005 What's Wrong with A Cascaded Correlation Learning Network: A Projection Pursuit Learning Perspective Jenq-Neng Hwangy, Shih-Shien Youz, Shyh-Rong Layy, I-Chang Jouz.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smieja.pandemonium.ps.Z, 19931006 The Pandemonium System of Reflective Agents Frank Smieja October 6, 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR33.ps.gz, 19931007 On the Embedding of a Class of Regular Graphs in a Faulty Hypercube Yu-Chee Tseng and Ten-Hwang Lai Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 Tel: (614)292-5813, Fax: (614)292-2911 E-mail: ftseng, laig@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/beyer.explore.ps.Z, 19931011 Learning from Examples using Reflective Exploration Uwe Beyer Frank Smieja October 11, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/brousse.sysgen.ps.Z, 19931013 Generativity and Systematicity in Neural Network Combinatorial Learning Olivier Brousse Department of Computer Science & Institute of Cognitive Science University of Colorado Boulder, CO 80309{0430 olivier@cs.colorado.edu University of Colorado at Boulder Technical Report CU-CS-676-93 October 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR35.ps.gz, 19931018 1 OSU-CISRC-10/93-TR35 Volume Rendering Polyhedral Grids by Incremental Slicing Roni Yagel Department of Computer and Information Science The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sheppard.rl_in_control.ps.Z, 19931018 REINFORCEMENT LEARNING IN CONTROL M. Sheppard1, A. Oswald2, C. Valenzuela, G. Sullivan and R. Sotudeh University of Teesside, Middlesbrough, Cleveland, TS1 3BA, UK
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/phatak.nn-fault-tolerance.ps.Z, 19931020 Complete and Partial Fault Tolerance of Feedforward Neural Nets D. S. Phatak and I. Koren Department of Electrical and Computer Engineering University of Massachusetts, Amherst, MA 01003 Technical Report No. TR-92-CSE-26 y July 1992, last revised April 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/saul.boltzmann.ps.Z, 19931020 Learning in Boltzmann Trees Lawrence Sauly and Michael Jordanyy Department of Physicsy Department of Brain and Cognitive Sciencesyy Massachusetts Institute of Technology Cambridge, MA 02139 October 20, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/moriarty.othello.ps.Z, 19931104 EVOLVING COMPLEX OTHELLO STRATEGIES USING MARKER-BASED GENETIC ENCODING OF NEURAL NETWORKS David Moriarty and Risto Miikkulainen Department of Computer Sciences The University of Texas at Austin, Austin, TX 78712-1188 moriarty,risto@cs.utexas.edu Technical Report AI93-206 September 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR36.ps.gz, 19931105 Broadcasting in k-ary n-cube Wormhole Routed Networks using Path-based Routing 1 Dhabaleswar K. Panda and Sanjay Singal Department of Computer and Information Science Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email: fpanda,singalg@cis.ohio-state.edu Contact
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR37.ps, 19931109 Multicasting using Multidestination-Worms Conforming to Base Routing Schemes 1 Dhabaleswar K. Panda and Pradeep Prabhakaran Department of Computer and Information Science Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email: fpanda,prabhakag@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR38.ps.gz, 19931116 isi ility o utation for lanar yna ic cenes Prabhakaran Pradeep umar and ikuo Fujimura November 12, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rosen.scoring.ps.Z, 19931117 SCORING THE FORECASTER BY MEAN RESULTING PAYOFF OF A DISTRIBUTION OF DECISION PROBLEMS David B. Rosen Center for Biomedical Modeling Research University of Nevada School of Medicine 77 Pringle Way, H1-166 WMC Reno, Nevada 89520 USA Internet: rosen@unr.edu (or d.rosen@ieee.org) Presented at the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/smagt.hand-eye.ps.Z, 19931119 Robot hand-eye coordination using neural networks TR CS{93{10 Patrick van der Smagt Frans Groen Ben Kr ose University of Amsterdam Department of Computer Systems Kruislaan 403 1098 SJ Amsterdam email October 25, 1993 This paper focuses on static hand-eye coordination. The key issue
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/biehlmietzner.pancakes.ps.Z, 19931122 Statistical Mechanics of Unsupervised Structure Recognition Michael Biehl and Andreas Mietzner Physikalisches Institut, Julius{Maximilians{Universit at Am Hubland, D{97074 W urzburg, Germany
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.paradox.ps.Z, 19931124 The Observers Paradox: Apparent Computational Complexity in Physical Systems John F. Kolen and Jordan B. Pollack To appear Summer 1994 in The Journal of Experimental and Theoretical Artificial Intellignce Running Head: The Observers Paradox August 15, 1993 Laboratory for Artificial Intelligence Research
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/williams.perf-bound.ps.Z, 19931129 Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions Ronald J. Williams College of Computer Science Northeastern University Boston, MA 02115 rjw@ccs.neu.edu Leemon C. Baird, III Wright Laboratory Wright-Patterson Air Force Base, OH 45433-6543 bairdlc@wL.wpafb.af.mil
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/luttrell.part-mixture.ps.Z, 19931129 Submitted to a Special Issue of IEE Proceedings on Vision, Image and Signal Processing Created 29 November 1993 An earlier version of this paper appeared in the Proceedings of the International Conference on Artificial Neural Networks, Brighton, 1993, pp. 313-316 The Partitioned Mixture Distribution: An
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/siegelmann.prob.ps.Z, 19931130 ON THE COMPUTATIONAL POWER OF FAULTY AND ASYNCHRONOUS NEURAL NETWORKS Hava T. Siegelmann Department of Computer Science Bar-Ilan University, Ramat-Gan 52900, Israel E-mail: hava@bimacs.cs.biu.ac.il
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yuyi.online_rbf.ps.Z, 19931203 ON-LINE STABLE NONLINEAR MODELLING BY STRUCTURALLY ADAPTIVE NEURAL NETS Shaohua Tan, Yi Yu Department of Electrical Engineering National University of Singapore 10 Kent Ridge Crescent, Singapore 0511
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/3-Chapter3.ps.gz, 19931207 89 CHAPTER III Additional Capabilities, Support for Testing and Debugging, and Partial Instantiation The previous chapter introduced principles for constructing a component s interface. It also introduced principles to be followed when implementing a component. This chapter discusses how to add various
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/7-Bibliography.ps.gz, 19931207 225 BIBLIOGRAPHY Department of Defense, Ada Joint Program Office, Reference Manual for the Ada Programming Language, ANSI/MIL-STD- 1815A, Government Printing Office, Washington, D.C., 1983. Bentley, J.L., More Programming Pearls, Addison-Wesley, Menlo Park, California, 1988.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/1-Chapter1.ps.gz, 19931207 1 CHAPTER I Introduction The software crisis has been with us for quite some time , and is not diminishing. A recent Software Engineering Institute (SEI) report identifies capacity to produce software over the near-term as a critical problem . The report states that
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/5-Chapter5.ps.gz, 19931207 173 CHAPTER V Conclusion In this chapter, we summarize the research conducted for this dissertation and present conclusions drawn from the work. Next we present contributions to the field and conclude with a discussion of some open issues and possible future work. 5.1 Summary and Conclusions The primary
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/6.4-AppendixD.ps.gz, 19931207 219 APPENDIX D Compendium of Principles Principle 1 Make generic packages the unit of modularity. Physically separate the package specification and the package body by placing them in separate files. Principle 2 Export a type so that abstract state is maintained in variables of that type, not in package
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/6.1-AppendixA.ps.gz, 19931207 179 APPENDIX A Component Specifications In this appendix we provide specifications for the One_Way_List_Template, Two_Way_List_Template, N_Way_Nilpotent_Template, Tuple2_Model_Template, and Set_Model_Template. Other specifications that appear throughout the dissertation are listed below: Queue_15
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/0.2-Contents.ps.gz, 19931207 ii To my parents, Martha and Charles Hollingsworth, my wife, Janet Vician Hollingsworth, and children, Emma Jean and Max Wilson. iii ACKNOWLEDGMENTS Sincere thanks goes to Bruce Weide, my adviser. Without your guidance, patience and seemingly limitless interest in my research, I would have made too many
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/6.2-AppendixB.ps.gz, 19931207 197 APPENDIX B Component Implementations In this appendix we provide implementations for the Built_In_Types package, Static_Array_Template, One_Way_Nilpotent_Template, and Permutation_Template. Other implementations that appear throughout the dissertation are listed below: Queue_15 Section 2.3
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/2-Chapter2.ps.gz, 19931207 11 CHAPTER II First Principles for Constructing Components in Ada In this chapter we fix the programming language to be Ada and the component type to be abstract data types. We introduce principles for constructing Ada components that have abstraction barriers with no implementation leaks. This is
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/4-Chapter4.ps.gz, 19931207 127 CHAPTER IV Bootstrapping From Raw Ada Being able to use Ada s built-in scalar types (i.e., Boolean, Character, Float or Integer) is primarily a matter of convenience. We could, if we desired, create our own package for each of these scalar types. On the other hand, constructing any non-trivial
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/6.3-AppendixC.ps.gz, 19931207 217 APPENDIX C RESOLVE/Ada Naming and Formatting Conventions Use underscores in all identifiers to separate words. For math/theory modules, math types, and math functions use all upper case. o For math/theory modules use the form THEORY_NAME_THEORY_TEMPLATE (e.g., STRING_THEORY_TEMPLATE). o For math
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR01-DIR/0.1-Title.ps.gz, 19931207 Software Component Design-for-Reuse: A Language-Independent Discipline Applied to Ada DISSERTATION Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the Graduate School of the Ohio State University By Joseph Eugene Hollingsworth, B.S., M.S. The Ohio State
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR43.ps.gz, 19931208 M. Theimer, K. Lantz, and D. Cheriton, Preemptable Remote Execution Facilities for the V-System, Proc. Tenth ACM Symposium On Operating System Principles, pp. 2-12, Dec. 1985. E. Zayas, Attacking the Process Migration Bottleneck, Proc. Eleventh ACM Symposium On Operating System Principles, pp.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR39.ps.gz, 19931208 A Universal Framework for Data Transformation John A. Gawkowski R.R. Donnelley & Sons Database Technology Services 7501 S. Quincy Street Willowbrook. Ill 60521-5544 email: jgawkowski@rrddts.donnelley.com S.A. Mamrak Department of Computer and Information Science The Ohio State University email:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR41.ps.gz, 19931208 e er e r r cess r et r s anas andal, ahendra amachandran and rasad ishnu hotla epartment of omputer and Information cience he hio tate niversit , olum us, hio 1 -1 e a : a s s. -s a e.e The LPS ernel for Processor etworks
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/siegelmann.training.ps.Z, 19931209 On the Complexity of Training Neural Networks with Continuous Activation Functionsz Bhaskar DasGupta Department of Computer Science University of Minnesota Minneapolis, MN 55455-0159 Email: dasgupta@cs.umn.edu Hava T. Siegelmanny Department of Computer Science Bar-Ilan University Ramat-Gan 52900, Israel
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR42.ps.gz, 19931209 stract n this paper, we introduce the concept of infection. nfection helps in keeping track of the causal dependencies in a distributed computation. ecovery algorithms with synchronous checkpointing re uire periodic collection of consistent snapshot of the system to advance the checkpoint. revious
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jacobs.rfield.ps.Z, 19931213 Encoding Shape and Spatial Relations: The Role of Receptive Field Size in Coordinating Complementary Representations Robert A. Jacobs Department of Psychology University of Rochester Rochester, NY 14627 Stephen M. Kosslyn Department of Psychology Harvard University Cambridge, MA 02138 Date: November
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/marshall.occlusion.ps.Z, 19940105 A Self-Organizing Neural Network That Learns to Detect and Represent Visual Depth from Occlusion Events Jonathan A. Marshall and Richard K. Alley Department of Computer Science, CB 3175, Sitterson Hall University of North Carolina, Chapel Hill, NC 27599-3175, U.S.A. marshall@cs.unc.edu, alley@cs.unc.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/weigl.NNdynabase.ps.Z, 19940105 ISSN 0249-6399INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUEflapport de recherchefl1993flPROGRAMME 4flRobotique,flimageflet visionfl Neural Networks as Dynamical Bases in Function Space Konrad Weigl & Marc Berthod N 2124 December 1993 Neural Networks as Dynamical Bases in Function
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nowlan.nips94.ps.Z, 19940107 Mixtures of Controllers for Jump Linear and Non-linear Plants Timothy W. Cacciatore Department of Neurosciences University of California at San Diego La Jolla, CA 92093 Steven J. Nowlan Synaptics, Inc. 2698 Orchard Parkway San Jose, CA 95134
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/plate.nips93.ps.Z, 19940110 To appear in J. D. Cowan, G. Tesauro, and J. Alspector, editors, Advances in Neural Information Processing Systems - 6 - (NIPS*93), Morgan Kaufmann, San Mateo, CA Estimating analogical similarity by dot-products of Holographic Reduced Representations. Tony A. Plate Department of Computer Science,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR46.ps.gz, 19940110 Closure Properties and Witness Reduction Sanjay Gupta1 Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 1This work was supported in part by NSF under Grant No. CCR-8909071. WITNESS REDUCTION Sanjay Gupta Department of Computer and Information Science The Ohio
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.foolsgold.ps.Z, 19940111 John F. Kolen Laboratory for Artificial Intelligence Research Department of Computer and Information Science The Ohio State University Columbus, OH 43210 kolen-j@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/siegelmann.kolmogorov.ps.Z, 19940111 Computational Power of Neural Networks: A Kolmogorov Complexity Characterization Jos e L. Balc azary Ricard Gavald ay Department of Software (LSI) Universitat Polit ecnica de Catalunya, Barcelona 08028, Spain E-mail: balqui@lsi.upc.es, gavalda@lsi.upc.es Hava T. Siegelmannz Department of Mathematics and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR40.ps.gz, 19940111 Improving Reusability by Recasting Single Large-Effect Operations as Objects Bruce W. Weide William F. Ogden Department of Computer and Information Science The Ohio State University Columbus, OH 43210 {weide,ogden}@cis.ohio-state.edu Murali Sitaraman Department of Statistics and Computer Science West
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shadmehr.elements.ps.Z, 19940111 Computational Elements of the Adaptive Controller of the Human Arm Reza Shadmehr and Ferdinando A. Mussa-Ivaldi Dept. of Brain and Cognitive Sciences M. I. T., Cambridge, MA 02139 Email: reza@ai.mit.edu, sandro@ai.mit.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gorse.reinforce.ps.Z, 19940112 A PULSE-BASED REINFORCEMENT ALGORITHM FOR LEARNING CONTINUOUS FUNCTIONS D Gorse Department of Computer Science University College, Gower Street, London WC1E 6BT, UK J G Taylor Department of Mathematics T G Clarkson Department of Electrical and Electronic Engineering King's College, Strand, London WC2R
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gorse.homotopy.ps.Z, 19940112 A CLASSICAL ALGORITHM FOR AVOIDING LOCAL MINIMA D Gorse and A Shepherd Department of Computer Science University College, Gower Street, London WC1E 6BT, UK J G Taylor Department of Mathematics King's College, Strand, London WC2R 2LS, UK Conventional methods of supervised learning are inevitably faced
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/das.dolce.ps.Z, 19940115 A Unified Gradient-Descent/Clustering Architecture for Finite State Machine Induction Sreerupa Das and Michael C. Mozer Department of Computer Science University of Colorado Boulder, CO 80309{0430
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hinton.autoencoders.ps.Z, 19940117 Autoencoders, Minimum Description Length and Helmholtz Free Energy Geoffrey E. Hinton Department of Computer Science University of Toronto 6 King's College Road Toronto M5S 1A4, Canada Richard S. Zemel Computational Neuroscience Laboratory The Salk Institute 10010 North Torrey Pines Road La Jolla, CA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zemel.dubm.ps.Z, 19940117 Lending Direction to Neural Networks Richard S. Zemel1 Christopher K. I. Williams 1 Michael C. Mozer2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zemel.pop-codes.ps.Z, 19940117 Developing Population Codes By Minimizing Description Length Richard S. Zemel CNL, The Salk Institute 10010 North Torrey Pines Rd. La Jolla, CA 92037 Geoffrey E. Hinton Department of Computer Science University of Toronto Toronto M5S 1A4 Canada
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yzhao.theory-pp.ps.Z, 19940118 Projection Pursuit Learning: Approximation Properties Ying Zhao1 and Christopher G. Atkeson MIT Artificial Intelligence Laboratory and the Department of Brain and Cognitive Sciences NE43-771, 545 Technology Square Cambridge, MA 02139 617-253-0788 yzhao@bbn.com, cga@ai.mit.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kirkpatrick.critical.ps.Z, 19940118 Critical Behavior at the k-Satisfiability Threshold Scott Kirkpatrick IBM TJ Watson Research Center Yorktown Heights, NY 10598 kirk@watson.ibm.com Bart Selman AT&T Bell Laboratories Murray Hill, NJ 07974 selman@research.att.com
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mitchell.ga-hillclimb.ps.Z, 19940118 When Will a Genetic Algorithm Outperform Hill Climbing Melanie Mitchell Santa Fe Institute 1660 Old Pecos Trail, Suite A Santa Fe, NM 87501 John H. Holland Dept. of Psychology University of Michigan Ann Arbor, MI 48109 Stephanie Forrest Dept. of Computer Science University of New Mexico Albuquerque, NM
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/yzhao.implement-pp.ps.Z, 19940118 Implementing Projection Pursuit Learning Ying Zhao 1 and Christopher G. Atkeson MIT Artificial Intelligence Laboratory and the Department of Brain and Cognitive Sciences NE43-771, 545 Technology Square Cambridge, MA 02139 617-253-0788 yzhao@bbn.com, cga@ai.mit.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kirkpatrick.nips93-statistical.ps.Z, 19940118 The Statistical Mechanics of k-Satisfaction Scott Kirkpatrick Racah Institute for Physics and Center for Neural Computation Hebrew University Jerusalem, 91904 Israel kirk@fiz.huji.ac.il G eza Gy orgyi Institute for Theoretical Physics E otv os University 1-1088 Puskin u. 5-7 Budapest, Hungary
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shouval.pca.ps.Z, 19940118 Localized Principal Components of Natural Images - an Analytic Solution Yong Liu Harel Shouval Department of Physics Institute for Brain and Neural Systems Box 1843, Brown University Providence, R. I., 02912 yong@cns.brown.edu hzs@cns.brown.edu January 18, 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cauwenberghs.nips93.ps.Z, 19940119 A Learning Analog Neural Network Chip with Continuous-Time Recurrent Dynamics Gert Cauwenberghs California Institute of Technology Department of Electrical Engineering 128-95 Caltech, Pasadena, CA 91125 E-mail: gert@cco.caltech.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR01.ps.gz, 19940121 Designing Large Hierarchical Multiprocessor Systems under Processor, Interconnection, and Packaging Advancements 1 Debashis Basak and Dhabaleswar K. Panda Department of Computer and Information Science Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR02.ps.gz, 19940121 Intro uction A distributed computing system consists of spatially separated processes that do not share a common memory and that communicate with each other by message passing over communication channels. The system can be described as a directed graph in which vertices represent the processes and edges
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR03.ps.gz, 19940126 Compiling for Hierarchical Shared-Memory Multiprocessors J. D. Martens and D. N. Jayasimha Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210-1277 (614) 292-1932 martens@cis.ohio-state.edu jayasim@cis.ohio-state.edu January 24, 1994 A preliminary version of the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/jacobs.thesis4.ps.Z, 19940131 C h a p t e r 6 TASK DECOMPOSITION AND NETWORK ARCHITECTURES The previous two chapters reported the ability of the modular architecture to perform task decomposition on the what" and where" vision tasks and on the multi{payload robotics task. This chapter considers some domain{independent issues
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/gherrity.thesis.ps.Z, 19940131 UNIVERSITY OF CALIFORNIA, SAN DIEGO A Game-Learning Machine A dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Computer Science by Michael Gherrity Committee in charge: Professor Paul R. Kube, Chairperson Professor Richard K. Belew Professor
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/perrone.thesis.ps.Z, 19940131 Improving Regression Estimation: Averaging Methods for Variance Reduction with Extensions to General Convex Measure Optimization by Michael Peter Perrone B. S., Worcester Polytechnic Institute, 1987 Sc. M., Brown University, 1989 Thesis Submitted in partial fulfillment of the requirements for the Degree
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR06.ps.gz, 19940131 Stealth: A Liberal Approach to Distributed Scheduling for Networks of Workstations Phillip Krueger and Davender Babbar Department of Computer and Information Science Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/boyan.backgammon-thesis.ps.Z, 19940131 E-mail: Justin.Bo y an@cs.cmu.edu b y B.S., University of Chicago (1991) c Justin A. Boyan, 1992 UNIVERSITY OF CAMBRIDGE Submitted to the Department of Engineering and Computer Laboratory in partial fulfillme n t of the requirements for the degree of Master of Philosophy Computer Speec h and Language
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR04.ps.gz, 19940131 On Local Certifiability of Software Components Bruce W. Weide Department of Computer and Information Science The Ohio State University Columbus, OH 43210 weide@cis.ohio-state.edu Joseph E. Hollingsworth Department of Computer Science Indiana University Southeast New Albany, IN 47150
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/zemel.thesis2.ps.Z, 19940131 4.3. EXPERIMENTAL RESULTS 71 Figure 4.6: This figure shows the incoming and outgoing weights for the 30 representation units in a network trained on the dual-component dataset. For each unit, the input weights are shown below the output weights, and both sets are split in half, corresponding to the two
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/jacobs.thesis1.ps.Z, 19940131 Task Decomposition Through Competition in a Modular Connectionist Architecture Robert A. Jacobs Department of Computer & Information Science University of Massachusetts, Amherst, MA 01003 COINS Technical Report 90{44 May 1990 TASK DECOMPOSITION THROUGH COMPETITION IN A MODULAR CONNECTIONIST ARCHITECTURE
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/page.thesis.ps.Z, 19940131 Contents 1 Introduction 6 2 Aspects of Music Psychology 11 2.1 Introduction : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 11 2.2 What are the perceived elements of melody : : : : : : : : : : : : : : : : : : : 11 2.2.1 Review of experiments : : : : : : : : : : : : : : : : : :
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/jacobs.thesis2.ps.Z, 19940131 C h a p t e r 3 A MODULAR CONNECTIONIST ARCHITECTURE In this chapter we introduce a modular connectionist architecture that learns to partition a task into two or more functionally independent tasks and allocates distinct networks to learn each task. 3.1 Output of the Architecture The architecture
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/becker.thesis3.ps.Z, 19940131 100 CHAPTER 6. DISCOVERING SPATIAL COHERENCE WITH BOLTZMANN MACHINES connections. This is not surprising, since these weights did not affect the states of units in the non-settling case; so a pair of units which learned, for example, to respond to left-shifted patterns, could theoretically keep
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/pratt.thesis.ps.Z, 19940131 144 Jakub Wejchert and Gerald Tesauro. Neural Network Visualization. In D. S. Touretzky, editor, Advances in Neural Information Processing Systems 2, pages 46572. Morgan Kaufmann, San Mateo, CA, 1990. P. Werbos. Beyond regression: New tools for prediction
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/plaut.thesis-summary.ps.Z, 19940131 Thesis Summary Connectionist Neuropsychology: The Breakdown and Recovery of Behavior in Lesioned Attractor Networks David C. Plaut School of Computer Science Carnegie Mellon University dcp@cs.cmu.edu September 1991 Thesis available as TR CMU-CS-91-185 Chapters 1 and 2: Introduction and background
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/zemel.thesis1.ps.Z, 19940131 A Minimum Description Length Framework for Unsupervised Learning by Richard S. Zemel A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Graduate Department of Computer Science University of Toronto c Copyright by Richard S. Zemel 1993 i
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/heermann.thesis2.ps.Z, 19940131 CHAPTER V CONTROL ARCHITECTURE 5.1 Proposed Architecture The controller architecture was designed with the goal of providing a nonlinear learning controller with stability assurances. Central to the controller design process was the feasibility for actual field use. Care was taken not to make
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/jacobs.thesis3.ps.Z, 19940131 C h a p t e r 5 MULTI{PAYLOAD ROBOTICS TASK The previous chapter showed that the modular architecture's rate of learning may be relatively unaffected by the inconsistent training information that characterizes temporal crosstalk. This chapter shows that this robustness leads to superior performance on
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/lambert.thesis.ps.Z, 19940131 Copyright by Bruce Laurence Lambert, 1992 A CONNECTIONIST MODEL OF MESSAGE DESIGN BY BRUCE LAURENCE LAMBERT A.B., University of Illinois at Urbana-Champaign, 1987 A.M., University of Illinois at Urbana-Champaign, 1988 THESIS Submitted in partial fulfillment of the requirements for the degree of Doctor
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/heermann.thesis1.ps.Z, 19940131 NEURAL NETWORK TECHNIQUES FOR STABLE LEARNING CONTROL OF NONLINEAR SYSTEMS Approved by Dissertation Committee: Copyright by Philip Dale Heermann 1992 All Rights Reserved Dedicated to Austin and Nathan NEURAL NETWORK TECHNIQUES FOR STABLE LEARNING CONTROL OF NONLINEAR SYSTEMS by PHILIP DALE HEERMANN,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/zemel.thesis3.ps.Z, 19940131 5.4. EXPERIMENTAL RESULTS 91 Figure 5.10: This figure shows the outgoing weights for a CVQ network with 5 VQs and 6 units per VQ. The first four rows depict the weights of the units in the first four VQs. Each VQ responds to curve segments between a particular pair of control points. The weights of the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/zhu.thesis.ps.Z, 19940131 NEURAL NETWORKS AND ADAPTIVE COMPUTERS THEORY AND METHODS OF STOCHASTIC ADAPTIVE COMPUTATION HUAIYU ZHU University of Liverpool Ph.D. Thesis 1993 Neural Networks and Adaptive Computers: Theory and Methods of Stochastic Adaptive Computation Thesis submitted in accordance with the requirements of the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/heermann.thesis3.ps.Z, 19940131 136 controller had maintained control for 0.25 hours, the system was pushed with a 20 newton force. The force continued until the reflexive stabilizer was needed. Each force was applied in a randomly selected direction. This is shown in Figure 7.6. Figure 7.6: Extended simulation of reflexive stabilizer
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/becker.thesis1.ps.Z, 19940131 An Information-theoretic Unsupervised Learning Algorithm for Neural Networks by Suzanna Becker A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Graduate Department of Computer Science University of Toronto c Copyright by Suzanna Becker 1992 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/becker.thesis2.ps.Z, 19940131 50 CHAPTER 3. COHERENCE-BASED UNSUPERVISED LEARNING: DISCRETE IMAX a b b) 1111111111111111 1111111111111111 maximize I 1 1 a b a) maximize I 1 1 1 1 Figure 3.7: a) Two units receive as input random binary patterns in which the left half is a shifted version of the right half. The inputs to the two units
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr1-94-hier_sys.ps.Z, 19940201 Designing Large Hierarchical Multiprocessor Systems under Processor, Interconnection, and Packaging Advancements Debashis Basak and Dhabaleswar K. Panda Technical Report OSU-CIS 1994/TR01 1 Designing Large Hierarchical Multiprocessor Systems under Processor, Interconnection, and Packaging Advancements 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/goodhill.normalization.ps.Z, 19940202 To appear in NEURAL COMPUTATION 6:2 The Role of Weight Normalization in Competitive Learning Geoffrey J. Goodhill Harry G. Barrow University of Edinburgh University of Sussex Centre for Cognitive Science School of Cognitive & Computing Sciences 2 Buccleuch Place Falmer Edinburgh EH8 9LW Brighton BN1 9QH
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/goodhill.elastic.ps.Z, 19940202 To appear in NEURAL COMPUTATION Elastic Net Model of Ocular Dominance: Overall Stripe Pattern and Monocular Deprivation Geoffrey J. Goodhill & David J. Willshaw Centre for Cognitive Science University of Edinburgh 2 Buccleuch Place Edinburgh EH8 9LW UK
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wahba.nips93.ps.Z, 19940202 DEPARTMENT OF STATISTICS University of Wisconsin 1210 West Dayton St. Madison, WI 53706 TECHNICAL REPORT NO. 909 December 9 1993 Structured Machine Learning for `Soft' Classification with Smoothing Spline ANOVA and Stacked Tuning, Testing and Evaluation 1 by Grace Wahba, Yuedong Wang, Chong Gu, Ronald
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wang.optistop.ps.Z, 19940203 to appear in NIPS-6- 1993 Optimal Stopping and Effective Machine Complexity in Learning Changfeng Wang Department of Systems Sci. and Eng. University of Pennsylvania Philadelphia, PA, U.S.A. 19104 Santosh S. Venkatesh Department of Electrical Engineering University of Pennsylvania Philadelphia, PA,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolf.address-block.ps.Z, 19940203 Postal Address Block Location Using A Convolutional Locator Network Ralph Wolf and John C. Platt Synaptics, Inc. 2698 Orchard Parkway San Jose, CA 95134 January 7, 1994
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR05.ps.gz, 19940204 An Optimality Proof for Asynchronous Recovery Algorithms in Distributed Systems Mukesh Singhal Friedemann Mattern Dept. of Computer Dept. of Computer Science and Information Science University of Saarland The Ohio State University Im Stadtwald 36 Columbus, OH 43210 66123 Saarbr ucken USA Germany
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr11-93-clus.ps.Z, 19940207 Clustering and Intra-Processor Scheduling for Explicitly-Parallel Programs on Distributed-Memory Systems Vibha A. Dixit-Radiya and Dhabaleswar K. Panda OSU-CISRC-3/93-TR11 Updated on February 7, 1994 A short version of this report will appear in International Parallel Processing Symposium, 1994. i
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR06.ps.gz, 19940207 Task Scheduling in Heterogeneous Systems in the Presence of Channel Contention Ravi Prakash & Dhabaleswar K. Panda Department of Computer and Information Science The Ohio State University, Columbus, OH 43210. e-mail: fprakash, pandag@cis.ohio-state.edu Contact Author: Prof. Dhabaleswar K. Panda
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr18-93-asg.ps.Z, 19940207 Task Assignment on Distributed-Memory Systems with Adaptive Wormhole Routing Vibha A. Dixit-Radiya and Dhabaleswar K. Panda OSU-CISRC-4/93-TR18 Updated on February 7, 1994 A short version of this report appears in Symposium on Parallel and Distributed Processing, 1993, pp. 674-681. i Task Assignment on
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR07.ps.gz, 19940208 riority t ernets: ro ises an allen es Frank Adelstein ukesh Singhal Dept. of Computer and Information Science The Ohio State University 2036 Neil Avenue all Columbus, OH 43210-1277 Phone: (614) 292-4634 FA : (614) 292-2911 Internet: ffrank,singhal cis.ohio-state.edu February 7, 1994
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR11.ps.gz, 19940208 Clustering and Intra-Processor Scheduling for Explicitly-Parallel Programs on Distributed-Memory Systems Vibha A. Dixit-Radiya and Dhabaleswar K. Panda OSU-CISRC-3/93-TR11 Updated on February 7, 1994 A short version of this report will appear in International Parallel Processing Symposium, 1994. i
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR18.ps.gz, 19940208 Task Assignment on Distributed-Memory Systems with Adaptive Wormhole Routing Vibha A. Dixit-Radiya and Dhabaleswar K. Panda OSU-CISRC-4/93-TR18 Updated on February 7, 1994 A short version of this report appears in Symposium on Parallel and Distributed Processing, 1993, pp. 674-681. i Task Assignment on
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ahmad.correspondence.ps.Z, 19940210 To appear in: Cowan, J.D., Tesauro, G., and Alspector, J. (Eds.), Advances in Neural Information Processing Systems 6. San Francisco CA: Morgan Kaufmann, 1994. Feature Densities are Required for Computing Feature Correspondences Subutai Ahmad Interval Research Corporation 1801-C Page Mill Road, Palo
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/myllymaki.thesis.ps.Z, 19940210 University of Helsinki Department of Computer Science Series of Publications C, No. C-1993-67 Petri Myllym aki Bayesian Reasoning by Stochastic Neural Networks Department of Computer Science P. O. Box 26 (Teollisuuskatu 23) FIN-00014 University of Helsinki, Finland Helsinki, December 1993 The papers in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/burgess.hipmod.ps.Z, 19940210 A model of hippocampal function Neil Burgess , Michael Recce and John O'Keefe Dept. of Anatomy, University College, London WC1E 6BT, U.K. Neural Networks: Special Issue on Neurodynamics and Behaviour, 1994, in press.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/li-zhaoping.stereocoding.ps.Z, 19940210 Efficient Stereo Coding in the Multiscale Representation 1 To be published in Network: Computation in Neural Systems Zhaoping Li and Joseph J. Atick The Rockefeller University 1230 York Avenue New York, NY 10021, USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/indiveri.nn_defect_detect.ps.Z, 19940210 A Neural Network Architecture for Defect Detection through Magnetic Particle Inspection Giacomo Indiveri, Giovanni Nateri, Luigi Raffo, Daniele Caviglia Department of Biophysical and Electronic Engineering University of Genova-Via Opera Pia 11/A-16145 Genova-ITALY ph: +39 10 3532163, fax: +39 10
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/harley.aphasia.ps.Z, 19940210 Proc. 14th. Annual Conf. Cognitive Science Soc., Bloomington IN, 1992, pp. 378-383. 378 Modelling Paraphasias in Normal and Aphasic Speech Trevor A. Harley & Siobhan B. G. MacAndrew Department of Psychology University of Warwick Coventry CV4 7AL England EMAIL: psrds@csv.warwick.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cottrell.things.ps.Z, 19940210 Two or three things that we know about the Kohonen algorithm M.Cottrelly, J.C.Fortz, G.Pag es y Samos/Universit e Paris 1 90, rue de Tolbiac, F-756345 Paris Cedex 13, France z Samos et Universit e Nancy 1/D epartement de Math ematiques F-54506 Vandoeuvre-L es-Nancy Cedex, France Samos et Universit e
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/venugopal.thesis7.ps.Z, 19940211 1 REFERENCES J. D. Cowan and D. H. Sharp, ``Neural Nets, Quart. Rev. Bio Physics, vol. 21, no. 3, 1988, pp. 365 421. W. S. McCulloch and W. Pitts, ``A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biophysics, vol. 5, 1943, 115 133. D. O. Hebb, ``The organization of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/venugopal.thesis2.ps.Z, 19940211 1 ffl ff fl fl fl ffiflfl ffifl fiffi ff One of the important reasons for the increased interests in the recent times concerning the connectionist models, is the emergence of new network architectures, learning algorithms and the surmission that massive parallelism is essential for many of the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/venugopal.thesis3.ps.Z, 19940211 For: venu Printed on: Sat, Feb 5, 1994 15:58:50 Document: Ch__3 Last saved on: Sat, Feb 5, 1994 15:42:47 1 <= fl fl ff<= ffi >= ff fl fflffffl ffffl ffl >= fl ffl <= fi In this chapter, the Alopex algorithm is shown as an efficient supervised learning algorithm for neural networks. A brief
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/venugopal.thesis1.ps.Z, 19940211 fi ffi ffi ffi fflffiffi fflffi ffi ffl ff <= ffi fiffl fi ffl fl by ff$$) ! >=o#OE$% ! ((o') ) $# ss" ))ooe )$ )Oo ae!)+ $AE Oo $!!oOEo $AE #OE #oo' #OE # ') ! !AE !!"o#) $AE )Oo o&* 'o"o#)( AE$' )Oo oOE'oo $AE $ae)$' $AE O !$($%O+ # !oae)' ae ! #OE #oo' #OE Florida Atlantic University Boca Raton,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/venugopal.thesis6.ps.Z, 19940211 1 fl ffi SUMMARY AND CONCLUSIONS ffl ffff ffi fi ffi ffl ffl Through a number of experimental studies, it is shown that the Alopex algorithm can be used as an efficient learning algorithm for connectionist models. The problems studied include a number of standard benchmark problems such as XOR/Parity,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/venugopal.thesis5.ps.Z, 19940211 1 ff >= ffi fi >= ffi fflfi ffi <= <=>= ffl<= <=fi ffi >= fl<= >= fifi In the previous chapter, the existing direct control schemes for the on line learning control of dynamical systems were discussed in detail. Two modifications were proposed. It was shown that the proposed methods (gain layer schemes)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/venugopal.thesis4.ps.Z, 19940211 1 ff >= ffi fi >= ffi fflfi ffi <= <=>= ffl<= <=fi ffi >= fl<= >= fi In the previous chapter, the effectiveness of the Alopex as a learning algorithm was demonstrated on a number of static and temporal pattern recognition tasks. Even though the static recognition tasks are adequate to a certain extent
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/venugopal.css.ps.Z, 19940214 to appear in Journal of Circuits, Systems and Signal Processing 35 w wd Fig. 10b. to appear in Journal of Circuits, Systems and Signal Processing 34 q qd Fig. 10a to appear in Journal of Circuits, Systems and Signal Processing 33 command signal gain layer scheme feedback gain scheme Fig. 9. to appear in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/scheler.adaptive.ps.Z, 19940216 Pattern Classification with Adaptive Distance Measures G. Scheler Institut f ur Informatik Technische Universit at M unchen e-mail: scheler@informatik.tu-muenchen.de February 15, 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sollich.queries.ps.Z, 19940217 Query construction, entropy and generalization in Neural Network models Peter Sollich Department of Physics, University of Edinburgh, Kings Buildings, Mayfield Road, Edinburgh EH9 3JZ, U.K. (To appear in Physical Review E)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gold.object-clustering.ps.Z, 19940221 Clustering with a Domain-Specific Distance Measure Steven Gold, Eric Mjolsness and Anand Rangarajan Department of Computer Science Yale University New Haven, CT 06520-8285
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lu.object-matching.ps.Z, 19940221 Two-Dimensional Object Localization by Coarse-to-Fine Correlation Matching Chien-Ping Lu and Eric Mjolsness Department of Computer Science Yale University New Haven, CT 06520-8285
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cohn.explore.ps.Z, 19940224 To appear in J. Cowan et al., eds., Advances in Neural Information Processing Systems 6, Morgan Kaufmann, 1994. Note that this version contains a correction to Equation 2 that was too late to be included in print. Neural Network Exploration Using Optimal Experiment Design David A. Cohn Dept. of Brain
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fiesler.formalization.ps.Z, 19940224 Neural Network Classification and Formalization E. Fiesler IDIAP Case postale 609 CH-1920 Martigny Switzerland
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/andreou.vlsi-phase-lock.ps.Z, 19940228 VLSI Phase Locking Architectures for Feature Linking in Multiple Target Tracking Systems Andreas G. Andreou andreou@jhunix.hcf.jhu.edu Department of Electrical and Computer Engineering The Johns Hopkins University Baltimore, MD 21218 Thomas G. Edwards tedwards@src.umd.edu Department of Electrical
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zecchina.response.ps.Z, 19940228 Response Functions Improving Performance in Analogue Attractor Neural Networks Nicolas Brunel INFN, Dipartimento di Fisica, P.le Aldo Moro 2, 00185 Roma, Italy Riccardo Zecchinay Dip. di Fisica Teorica e INFN, Universit a di Torino, Via P.Giuria 1, 10125 Torino, Italy (February 24, 1994)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR09.ps.gz, 19940301 Optimal, Nonmasking Fault-Tolerant Reconfiguration of Trees and Rings Anish Arora Ashish Singhai Department of Computer Science Department of Computer Science The Ohio State University University of Illinois Columbus, OH 43210 Urbana-Champaign, IL 61801 December 10, 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maron.hoeffding.ps.Z, 19940302 Hoeffding Races: Accelerating Model Selection Search for Classification and Function Approximation Oded Maron Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge, MA 02139 Andrew W. Moore Robotics Institute School of Computer Science Carnegie Mellon University Pittsburgh,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/venugopal.alopex.ps.Z, 19940304 Alopex: A Correlation-Based Learning Algorithm for Feed-Forward and Recurrent Neural Networks K. P. Unnikrishnan, and K. P. Venugopal W
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/roebel.dynada.ps.Z, 19940307 The Dynamic Pattern Selection Algorithm: Eoeective Training and Controlled Generalization of Backpropagation Neural Networks A. R bel Technische Universit t Berlin1 March 4, 1994 1Institut f r Angewandte Informatik, FG Informatik in Natur- und Ingenieurwissenschaften
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hertz.nonlin.ps.Z, 19940308 Non-Linear Back-propagation: Doing Back-Propagation without Derivatives of the Activation Function. John Hertz Nordita, Blegdamsvej 17, 2100 Copenhagen, Denmark Email: hertz@nordita.dk Anders Krogh Electronics Institute, Technical University of Denmark, Building 349 2800 Lyngby, Denmark, Email:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kinder.extracting_invariants.ps.Z, 19940308 Classification of Trajectories - Extracting Invariants with a Neural Network M. Kinder , W. Brauer Institut f ur Informatik Technische Universit at M unchen Arcisstr. 21, 8000 M unchen 2 Germany
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/glasius.labyrinth.ps.Z, 19940308 Neural network dynamics for path planning and obstacle avoidance 1 R. Glasius A. Komoda S. Gielen Department of Medical Physics and Biophysics, University of Nijmegen, Geert Grooteplein Noord 21, 6525 EZ Nijmegen, The Netherlands,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wang.nnga.ps.Z, 19940308 NIBS Technical Report, TR-940216. Copyright (c) 1994 by NIBS Pte Ltd. All rights reserved. GENETICALLY OPTIMIZED NEURAL NETWORKS Francis Wong NIBS Pte Ltd, 62 Fowlie Rd, Singapore 1542 Geraldine Goh Accel Infotech (S) Pte Ltd accel@solomon.technet.sg 1. INTRODUCTION Recently, neural networks and genetic
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stiber.transient.ps.Z, 19940311 Transient Responses in Dynamical Neural Models Michael Stiber Department of Computer Science The Hong Kong University of Science and Technology Clear Water Bay, Kowloon Hong Kong email: stiber@cs.ust.hk Jos e P. Segundo Department of Anatomy and Cell Biology and Brain Research Institute University of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bishop.mixture2.ps.Z, 19940315 10200.00.51.0p (t \| x)txxx= 0.8= 0.5= 0.2 Figure 7: Plot of the conditional probability densities of the target data, for various values of x, obtained by taking vertical slices through the contours in Figure 6, for x = :2, x = :5 and x = :8. It is clear that the Mixture Density Network is able to
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/battiti.neuro-hep.ps.Z, 19940315 Learning with First, Second, and No Derivatives: a Case Study in High Energy Physics Roberto Battiti Dipartimento di Matematica, Universit a di Trento, 38050 Povo (Trento) - Italy and INFN, Gruppo Collegato di Trento e-mail: battiti@itnvax.cineca.it GIAMPIETRO TECCHIOLLI Istituto per la Ricerca
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/battiti.reactive-tabu-search.ps.Z, 19940315 1 The Reactive Tabu Search ROBERTO BATTITI Dipartimento di Matematica and Istituto Nazionale di Fisica Nucleare, gruppo collegato di Trento, Universit a di Trento, 38050 Povo (Trento), Italy, EMAIL: battiti@itnvax.science.unitn.it GIAMPIETRO TECCHIOLLI Istituto Nazionale di Fisica Nucleare, gruppo
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bolt.ftnn.ps.Z, 19940316 Technical Report: YCS 154 Investigating Fault Tolerance in Artificial Neural Networks George Bolt Advanced Computer Architecture Group Department of Computer Science University of York Heslington, York, YO1 5DD, U.K. 25/3/91 hhhhhhhhhhhhhhh This work was supported by SERC and also by a CASE sponsorship
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bishop.mixture1.ps.Z, 19940316 Mixture Density Networks Chris M. Bishop Neural Computing Research Group Department of Computer Science Aston University Birmingham. B4 7ET, U.K. c.m.bishop@aston.ac.uk (February 1994) Neural Computing Research Group Report NCRG/4288
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bolt.ft_mlp.ps.Z, 19940316 Fault Tolerant Multi-Layer Perceptron Networks George Bolt1 James Austin, Gary Morgan Technical Report: YCS 180 July 1992 Advanced Computer Architecture Group Department of Computer Science University of York Heslington, York, YO1 5DD, U.K. Tel: +44-904-432771 Fax:+44-904-432767
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR10.ps.gz, 19940316 Decentralized Semaphore Support in a Virtual Shared Memory System Mahendra Ramachandran and Mukesh Singhal Department of Computer and Information Science The Ohio State University, Columbus, Ohio 43210-1277 email: framach,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR11.ps.gz, 19940316 Multimedia on Local Area Networks Amr Elsaadany, Mukesh Singhal and Ming T. Liu Department of Computer and Information Science The Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/chen.dynamic_approx.ps.Z, 19940321 Appeared in IEEE Transactions on Neural Networks, Nov. issue, 1993. Approximations of Continuous Functionals by Neural Networks with Application to Dynamical Systems Tianping Chen1 and Hong Chen2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/chen.function_approx.ps.Z, 19940321 Accepted by IEEE Transactions on Neural Networks. (Manuscript submitted 1991.) Approximation Capability in C( Rn) by Multilayer Feedforward Networks and Related Problems Tianping Chen1, Hong Chen2 and Ruey-wen Liu3
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ienne.genes.ps.Z, 19940330 GENES IV: A Bit-Serial Processing Element for a Multi-Model Neural-Network Accelerator Paolo Ienne and Marc A. Viredaz Swiss Federal Institute of Technology Microcomputing Laboratory & Centre for Neuro-Mimetic Systems IN-F Ecublens, CH-1015 Lausanne E-mail: Paolo.Ienne@di.epfl.ch
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/levin.pruning.ps.Z, 19940330 Appears in Advances in Neural Information Processing 6, J. Cowan, G. Tesauro, and J. Alspector, eds., Morgan Kaufmann, San Mateo, CA, 1994 Fast Pruning Using Principal Components Asriel U. Levin, Todd K. Leen and John E. Moody Department of Computer Science and Engineering Oregon Graduate Institute P.O.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/soodak.suture.ps.Z, 19940330 Published in Biological Cybernetics 70, 303-309 (1994) Simulation of visual cortex development under lid-suture conditions: Enhancement of response specificity by a reverse-Hebb rule in the absence of spatially patterned input Robert E. Soodak The Rockefeller University 1230 York Avenue New York, NY
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/golden.wrongprob.ps.Z, 19940330 Making Correct Statistical Inferences 38 List of Mathematical Symbols 2 = member of = uppercase greek omega >= = lowercase greek lambda = uppercase greek gamma r = gradient operator = uppercase greek delta ! = lowercase greek omega ff = lowercase greek alpha = lowercase greek gamma O = greek chi W =
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/viredaz.e-arch93.ps.Z, 19940330 MANTRA I : An SIMD Processor Array for Neural Computation Marc A. Viredaz Swiss Federal Institute of Technology EPFL { LAMI, IN-F Ecublens, CH { 1015 Lausanne E-mail : viredaz@di.epfl.ch
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolf.mutual1.ps.Z, 19940330 LANL LA-UR-93-833, SFI TR-93-07-047 ESTIMATING FUNCTIONS OF PROBABILITY DISTRIBUTIONS FROM A FINITE SET OF SAMPLES Part II: Bayes Estimators for Mutual Information, Chi-Squared, Covariance, and other Statistics. by David R. Wolf1 and David H. Wolpert2 1 - Los Alamos National Laboratory, MS P940, Los
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mozer.musiccomp.ps.Z, 19940330 To appear in: Connection Science, 1994. Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multiscale processing Michael C. Mozer Department of Computer Science and Institute of Cognitive Science University of Colorado Boulder, CO 80309-0430 e-mail:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/leen.adaptmomentum.ps.Z, 19940330 Optimal Stochastic Search and Adaptive Momentum Todd K. Leen and Genevieve B. Orr Oregon Graduate Institute of Science and Technology Department of Computer Science and Engineering P.O.Box 91000, Portland, Oregon 97291-1000
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kambhatla.dimredn.ps.Z, 19940330 In Cowan, J.D., Tesauro, G., and Alspector, J. (eds.) Advances in Neural Information Processing Systems 6, 1994. San Francisco, CA, Morgan Kaufmann Publishers. Fast Non-Linear Dimension Reduction Nanda Kambhatla and Todd K. Leen Department of Computer Science and Engineering Oregon Graduate Institute of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/neuneier.cond_dens.ps.Z, 19940330 to appear in the proceedings of the ICANN'94 (INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS), Sorrento , Italy Estimation of Conditional Densities: A Comparison of Neural Network Approaches R.Neuneierz, F.Hergertz, W.Finnoff , D.Ormoneity z Siemens AG, Corporate Research and Development
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR18.ps.gz, 19940331 Lossless Compression of Volume Data James E. Fowlery Roni Yagelz yDepartment of Electrical Engineering zDepartment of Computer and Information Science The Ohio State University Columbus, Ohio 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/scheler.generate.ps.Z, 19940331 Multilingual Generation of Grammatical Categories Gabriele Scheler Institut f ur Informatik Technische Universit at M unchen 80290 M unchen scheler@informatik.tu-muenchen.de March 31, 1994
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR13.ps.gz, 19940331 Assume a scenario where a person has called a travel agent and asked for a seat on a popular flight, hence the person knows the chances of getting on that flight are slim. The travel agent says, I am not finding anything then . Assume the parser provides the information that the sentence is declarative,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR15.ps.gz, 19940331 The Power of Carry-Save Addition D. R. Lutz D. N. Jayasimha Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 flutz-d,jayasimg@cis.ohio-state.edu March 31, 1994
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR12.ps.gz, 19940331 Maximal Global Snapshot with Concurrent Initiators Ravi Prakash and Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210. e-mail: fprakash, singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR14.ps.gz, 19940331 Real-Time Causal Message Ordering In Multimedia Systems Frank Adelstein Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, Ohio, 43210
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR16.ps.gz, 19940401 1 Visibility Computation for Interactive Visualization of Complex Enclosed Environments Roni Yagel and William Ray Department of Computer and Information Science The Ohio State University, Columbus, OH
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/simon.thesis.ps.Z, 19940401 Constructive Supervised Learning Algorithms for Artificial Neural Networks Natalio Simon 1 Delft University of Technology Faculty of Electrical Engineering Type Master Thesis Number of Pages 97 Date 4 juni 1993 Department Computer Architecture and Digital Technique Codenumber 1-68340-28(1993)06 Author
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/marks.fourier.ps.Z, 19940404 Fourier Analysis and Filtering of a Single Hidden Layer Perceptron Robert J. Marks II, Payman Arabshahi Department of Electrical Engineering, University of Washington FT{10 Seattle, WA 98195 USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/millan.sab94.ps.Z, 19940407 Learning E cient Reactive Behavioral Sequences from Basic Re exes in a Goal-Directed Autonomous Robot Jos e del R. MILL AN Institute for Systems Engineering and Informatics Commission of the European Communities. Joint Research Centre TP 361. 21020 ISPRA (VA). ITALY e-mail: jose.millan@cen.jrc.it
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR21.ps.gz, 19940411 The Effects of Layering and Encapsulation on Software Development Cost and Quality Stu Zweben, Steve Edwards, Bruce Weide The Ohio State University Joe Hollingsworth Indiana University Southeast y April 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ienne.nnarch.ps.Z, 19940412 epfl.epsf 24 22 mm ECOLE POLYTECHNIQUE F ED ERALE DE LAUSANNE Swiss Federal Institute of Technology, Lausanne Microcomputing Laboratory Architectures for Neuro-Computers: Review and Performance Evaluation Paolo Ienne Technical Report no. 93/21 January 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/omlin.dfa_encoding.ps.Z, 19940426 Constructing Deterministic Finite-State Automata in Recurrent Neural Networksy Christian W. Omlin a;b, C. Lee Giles a;c a NEC Research Institute, 4 Independence Way, Princeton, NJ 08540 b CS Department, Rensselaer Polytechnic Institute, Troy, NY 12180 c UMIACS, U. of Maryland, College Park, MD 20742
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hendin.olfaction.ps.Z, 19940426 Decomposition of a Mixture of Signals in a Model of the Olfactory Bulb O. HENDIN and D. HORN School of Physics and Astronomy Raymond and Beverly Sackler Faculty of Exact Sciences Tel Aviv University, Tel Aviv 69978, Israel J. J. HOPFIELD Divisions of Chemistry and Biology California Institute of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bishop.noise.ps.Z, 19940506 Training with Noise is Equivalent to Tikhonov Regularization Chris M Bishop Neural Computing Research Group Dept. of Computer Science Aston University Birmingham, B4 7ET, U.K. April 1994 Neural Computing Research Group Report NCRG/4290 (Accepted for publication in Neural Computation)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR24-DIR/text.ps.gz, 19940506 Polyhedral Shapes as General Implicit Surface Primitives Karansher Singh and Richard Parent Department of Computer and Information Science The Ohio State University 2036 Neil Avenue, Columbus, OH 43210 USA 15 November 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zimmer.navigation.ps.Z, 19940509 IIZUKA 94, Fukuoka, Japan August 1-7, 1994 Navigation on Topologic Feature-Maps Uwe R. Zimmer, Cornelia Fischer & Ewald von Puttkamer University of Kaiserslautern - Computer Science Department - Research Group Prof. E. v. Puttkamer 67663 Kaiserslautern - Germany Phone: 49 631 205 2624 - Fax: 49 631 205
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR45.ps.gz, 19940509 Fault Tolerance in a Multisensor Environment D. N. Jayasimha Department of Computer and Information Science 1 The Ohio State University 2036, Neil Ave. Columbus, OH 43210, USA Email: jayasim@cis.ohio-state.edu Revised: May 1994 1On leave at NASA Lewis Research Center & Ohio Aerospace Institute
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/hashem.thesis.ps.Z, 19940509 OPTIMAL LINEAR COMBINATIONS OF NEURAL NETWORKS1 A Thesis Submitted to the Faculty of Purdue University by Sherif Hashem In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy December 1993 c Copyright 1993 by Sherif Hashem. Internet: shashem@ecn.purdue.edu 1TECHNICAL REPORT
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zimmer.visual_search.ps.Z, 19940509 IIZUKA 94, Fukuoka, Japan August 1-7, 1994, Invited paper Connectionist Decision Systems for a Visual Search Problem Uwe R. Zimmer University of Kaiserslautern - Computer Science Department - Research Group Prof. E. v. Puttkamer 67663 Kaiserslautern - Germany Phone: 49 631 205 2624 - Fax: 49 631 205
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/williams.wcci94.ps.Z, 19940511 Improving Classification Performance in the Bumptree Network by Optimising Topology with a Genetic Algorithm Bryn V. Williams, Richard T. J. Bostock, David Bounds and Alan Harget Department of Computer Science and Applied Mathematics, Aston University, Birmingham B4 7ET, UK williabv@cs.aston.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/dennis.thesis.ps.Z, 19940511 The Integration of Learning into Models of Human Memory Simon John Dennis BSc (Hons), BA A thesis submitted for the degree of Doctor of Philosophy Department of Computer Science The University of Queensland March 28, 1994 MEMORY! Always there, of course, but usually hidden. And then, sometimes, as a
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/williams.ecal_93.ps.Z, 19940511 1 Learning and Evolution in Populations of Backprop Networks B V Williams and D G Bounds Department of Computer Science & Applied Mathematics Aston University, Aston Triangle, Birmingham B4 7ET, England e-mail: williabv@cs.aston.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/seung.rigorous.ps.Z, 19940512 Rigorous Learning Curve Bounds from Statistical Mechanics David Haussler U.C. Santa Cruz Santa Cruz, California Michael Kearns AT&T Bell Laboratories Murray Hill, New Jersey H. Sebastian Seung AT&T Bell Laboratories Murray Hill, New Jersey Naftali Tishby Hebrew University Jerusalem, Israel
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR25.ps.gz, 19940513 Skeletons and Techniques as a Normative Approach to Program Development in Logic-based Languages Technical Report OSU-CISRC-5/94-TR25 Marc Kirschenbaum Spiro Michaylovy Leon Sterlingz May 13, 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ginzburg.correlations.ps.Z, 19940517 Theory of Correlations in Stochastic Neural Networks Iris Ginzburg School of Physics and Astronomy Beverly and Raymond Sackler Faculty of Exact Sciences Tel-Aviv University, Tel-Aviv 69978, Israel Haim Sompolinsky Racah Institute of Physics and Center for Neural Computation Hebrew University, Jerusalem
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kruschke.baserates.ps.Z, 19940517 The Role of Base Rates in Category Learning John K. Kruschke Department of Psychology and Cognitive Science Program Indiana University, Bloomington IN 47405-4201 USA e-mail: kruschke@indiana.edu May 2, 1994 Indiana University Cognitive Science Program Research Report # 115 Copyright c 1994 by John K.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/meir.bias_variance.ps.Z, 19940518 Bias, variance and the combination of estimators; The case of linear least squares Ronny Meir Department of Electrical Engineering Technion, Haifa 32000 Israel rmeir@ee.technion.ac.il
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.perspectives.ps.Z, 19940518 to appear in: Theoretical Advances in Neural Computation and Learning, V. P. Roychowdhury, K. Y. Siu, A. Orlitsky, editors, Kluwer Academic Publishers Perspectives of Current Research about the Complexity of Learning on Neural Nets Wolfgang Maass Institute for Theoretical Computer Science Technische
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zimmer.topologic.ps.Z, 19940520 Euromicro 94 Realtime-Workshop Vaesteraas (V ster s), Sweden, June 15-17, '94 Realtime-learning on an Autonomous Mobile Robot with Neural Networks Uwe R. Zimmer & Ewald von Puttkamer University of Kaiserslautern - Computer Science Department - Research Group Prof. E. v. Puttkamer P.O. Box 3049 - 67663
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR26.ps.gz, 19940520 Fast Scanline Processing of Useful Implicitly-Defined Shapes: Sphylinders, Cone-Spheres and Rounded Polygons Karansher Singh and Richard Parent Department of Computer and Information Science The Ohio State University 2036 Neil Avenue, Columbus, OH 43210 USA 26 October 1993
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.nips-93.ps.Z, 19940526 19 The SFI tech. report that constitutes the full version of the paper Bayesian back-propagation over i-o functions rather than weights is not being stored in neuroprose. It can instead be found, compressed and/or compressed/uuencoded, under anonymous ftp at ftp.santafe.edu; once you ve logged in to the
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bishop.novelty.ps.Z, 19940527 Novelty Detection and Neural Network Validation Chris M. Bishop Neural Computing Research Group Department of Computer Science Aston University Birmingham, B4 7ET, U.K. c.m.bishop@aston.ac.uk (May 1994) To be published in IEE Proceedings, Special Issue on Applications of Neural Networks
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.learning-robot-navg.ps.Z, 19940531 A Lifelong Learning Perspective for Mobile Robot Control Sebastian Thrun Universit at Bonn Institut f ur Informatik III R omerstr. 164, 53117 Bonn, Germany E-mail: thrun@carbon.cs.bonn.edu to appear in: Proceedings of the IEEE Conference on Intelligent Robots and Systems to be held Sept. 12-16, 1994,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/berthold.tdrbf-icnn94.ps.Z, 19940602 A Time Delay Radial Basis Function Network for Phoneme Recognition Michael R. Berthold Intel Corporation, Santa Clara, CA95052, USA (to appear in Proceedings of the International Conference on Neural Networks, Orlando 1994)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ajjanagadde.aaai94.ps.Z, 19940604 To appear in Proceedings of the AAAI-94. Unclear Distinctions lead to Unnecessary Shortcomings: Examining the rule vs fact, role vs filler, and type vs predicate distinctions from a connectionist representation and reasoning perspective Venkat Ajjanagadde Wilhelm-Schickard Institute, Universitaet
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR17.ps.gz, 19940608 1 High Quality Template-Based Volume Rendering Roni Yagel and Kim Ciula Department of Computer and Information Science The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nolfi.erobot.ps.Z, 19940608 Institute of Psychology C.N.R. - Rome HOW TO EVOLVE AUTONOMOUS ROBOTS: DIFFERENT APPROACHES IN EVOLUTIONARY ROBOTICS Stefano Nolfi Dario Floreano Orazio Miglino *Francesco Mondada Institute of Psychology, National Research Council 15, Viale Marx - 00187 - Rome - Italy e-mail:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nolfi.plastic.ps.Z, 19940608 Institute of Psychology C.N.R. - Rome Phenotypic Plasticity in Evolving Neural Networks Stefano Nolfi+ Orazio Miglino* Domenico Parisi+ +Institute of Psychology, National Research Council, Rome, Italy. *Department of Psychology, University of Palermo, Italy e-mail:stefano@kant.irmkant.rm.cnr.it
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR27.ps.gz, 19940609 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bottou.effvc.ps.Z, 19940615 On the Effective VC Dimension L eon Bottou, Neuristique, 28 rue des Petites Ecuries, 75010 Paris Corinna Cortes & Vladimir Vapnik, AT&T Bell Laboratories, Holmdel NJ 07733, USA February 4, 1994
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR28.ps.gz, 19940615 1 Data-Parallel Volume Rendering Algorithms Roni Yagel and Raghu Machiraju Department of Computer and Information Science The Ohio State University Images generated from volumetric datasets are increasingly being used in many biomedical disciplines, archeology, geology, high energy physics,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wermter.screen.ps.Z, 19940616 Proceedings of the Twelfth National Conference on Artificial Intelligence, Seattle, 1994 Learning Fault-tolerant Speech Parsing with SCREEN Stefan Wermter and Volker Weber University of Hamburg, Computer Science Department Vogt-K olln-Strasse 30, D-22527 Hamburg, Germany
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/goodhill.nmds.ps.Z, 19940616 An evaluation of the use of Multidimensional Scaling for understanding brain connectivity Geoffrey J. Goodhill, Martin W. Simmen & David J. Willshaw University of Edinburgh Centre for Cognitive Science 2 Buccleuch Place Edinburgh EH8 9LW UK Research Paper EUCCS / RP-63, June 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shultz.cross.ps.Z, 19940620 1124 Lang, K. J., & Witbrock, M. J. (1988). Learning to tell two spirals apart. In D. Touretzky, G. Hinton, & T. Sejnowski (Eds)., Proceedings of the Connectionist Models Summer School, (pp. 52-59). Mountain View, CA: Morgan Kaufmann. McClelland, J. L. (1989). Parallel distributed processing:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/shivaratri/t1.ps.gz, 19940627 30 1 2 3 4 5 6 7 0.5 0.6 0.7 0.8 0.9 1.0 Offered System Load Mean Response Time M/M/1RANDOM SENDSYMRECVM/M/K Figure 4: Average Response Time vs. Offered System Load. was used for each of the algorithms. For these comparisons, a small fixed PollLimit (5) was assumed. We can see why such a small limit is
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/shivaratri/t5.ps.gz, 19940627 139 N. G. Shivaratri and M. Singhal. A Transfer Policy for Global Scheduling Algorithms to Schedule Tasks with Deadlines. In Proceedings of the 11th International Conference on Distributed Computing Systems, pages 24855, May 1991. M. Theimer, K. Lantz, and D. Cheriton. Preemptable Remote
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/shivaratri/t3.ps.gz, 19940627 90 1234567 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 Lower Threshold Free-Time Miss Ratio % X = 0.3 * SX = 0.5 * SX = 0.7 * S Figure 17: Mean miss ratio vs. LTFT. W = 0.9 (X + S), U = 0.7, UTFT = 1.05 S. reduced the waiting time of a remote task. These are the reasons why the miss ratio is higher at either
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/shivaratri/t2.ps.gz, 19940627 60 123456 5 10 15 20 25 30 35 40 Number of NLG Nodes Mean Response Time SENDADAPT-SEND Figure 9: Mean Response Time of SEND and ADAPT-SEND vs. Number of NLG nodes. Offered System Load = 0.85, Probelimit = 5, Threshold = 1, Mean Service Time = 1 section 3.4.1 with this sender-initiated adaptive location
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/shivaratri/t4.ps.gz, 19940627 110 i which indicates whether a task is in transit to node i; temp deposit queuei is a queue at node i to hold the Deposit messages received at i when i is requesting the token; temp token queuei is a queue at node i to hold the requests for the token while i is waiting for the token. In the algorithms
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bottou-effvc.ps.Z, 19940628 On the Effective VC Dimension L eon Bottou, Neuristique, 28 rue des Petites Ecuries, 75010 Paris Corinna Cortes & Vladimir Vapnik, AT&T Bell Laboratories, Holmdel NJ 07733, USA June 28, 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/pluto.thesis.ps.Z, 19940629 UNIVERSITY OF CALIFORNIA, SAN DIEGO Selecting Training Exemplars for Neural Network Learning A dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Computer Science and Engineering by Mark Plutowski Committee in charge: Professor Halbert White,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/massone.sensorimotor.ps.Z, 19940629 Sensorimotor Learning Lina L. E. Massone Dept. of Electrical Engineering and Computer Science Dept. of Biomedical Engineering Northwestern University 2145 Sheridan Road, Evanston, Il 60208 RUNNING HEAD: Sensorimotor Learning Correspondence: Prof. Lina L.E. Massone MEAS/EECS, Room Tech 1573 Northwestern
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR35.ps.gz, 19940629 A Note on Set Bit Enumeration Thomas Schwentick Johannes-Gutenberg Universit at Mainz tick@informatik.mathematik.uni-mainz.de J. Ramachandran Ohio State University ramachan@cis.ohio-state.edu June 28, 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lee.coling94.ps.Z, 19940701 Table-driven Neural Syntactic Analysis of Spoken Korean WonIl Lee, Geunbae Lee, Jong-Hyeok Lee Computer Science Deptartment of POSTECH. KOREA Tel: +82-562-279-2254, Fax: +82-562-279-2299
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pearson.clifford.ps.Z, 19940707 Clifford Networks An Introduction J.K.Pearson D.L.Bisset y Electronic Engineering Laboratories The University Canterbury Kent CT2 7NT U.K. February 23, 1994 Contents 1 Introduction 3 2 Clifford algebras an introduction. 7 2.1 Some familiar Clifford algebras : : : : : : : : : : : : : : : : : 9 2.1.1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/biehl.online.ps.Z, 19940707 Learning by Online Gradient Descent Michael Biehl CONNECT, The Niels Bohr Institute Blegdamsvej 17, 2100 Copenhagen O, Denmark Holm Schwarzey Department of Theoretical Physics, Lund University S olvegatan 14 A, 223 62 Lund, Sweden Lund University preprint LU TP 94{10
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/troyer.ffwd_hebb.ps.Z, 19940707 Feedforward Hebbian Learning 15 A.4 Proof of Theorem 4 We apply the Ghost Attractor Theorem. Fix a corner c, i.e. cffi = or 1. From equation (8) we have that the ghost attractor G(c) is given by G(c)ffi = X p xff x ci : (19) The region R(c) corresponding to c consists of all afferent input vectors a
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR34.ps.gz, 19940707 Distributed Semaphores Mahendra Ramachandran and Mukesh Singhal Department of Computer and Information Science The Ohio State University, Columbus, Ohio 43210-1277 email: framach,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR37.ps.gz, 19940711 Design of the Nagiya Editor Pete Ware July 5, 1994 Contents 1 Introduction to the Nagiya Editor 11 1.1 Acknowledgements : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 11 2 Manager Object Class 13 2.1 Purpose of the Manager Class : : : : : : : : : : : : : : : : : : : : : : : : : : : 13
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR38.ps.gz, 19940713 Priority Ethernets Frank Adelstein and Mukesh Singhal Dept. of Computer and Information Science The Ohio State University Columbus, OH 43210-1277
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/cwang.ps.gz, 19940714 Automatic Test Case Generation of Confromance Testing for Communication Protocols Specified in Extended Models By Chang-Jia Wang, Ph.D. The Ohio State University, 1994 Ming T. Liu, Adviser A communication protocol, which is a set of rules governing the operation of a computer network, is essential for
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR39.ps.gz, 19940714
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/biehl.online-perceptron.ps.Z, 19940715 On{line Learning with a Perceptron Michael Biehl CONNECT, The Niels Bohr Institute Blegdamsvej 17, Dk{2100 Copenhagen O, Denmark Peter Riegler + Institut f ur theoretische Physik Julius{Maximilians{Universit at W urzburg Am Hubland, D{97074 W urzburg, Germany
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/marangi.clusters.ps.Z, 19940715 Supervised learning from clustered input examples Carmela Marangi Dipartimento di Fisica dell'Universita' di Bari and I.N.F.N., Sez. di Bari Via Orabona 4, 70126 Bari, Italy Michael Biehl1 and Sara A. Solla2 CONNECT, The Niels Bohr Institute Blegdamsvej 17, 2100 Copenhagen O, Denmark
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/baldi.linear.ps.Z, 19940720 Learning in Linear Neural Networks: a Survey Pierre Baldi and Kurt Hornik, Member, IEEE
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/ray.spatiotemp.ps.Z, 19940720 A Temporal Sequence Processor Based on the Biological Reaction-Diffusion Process Sylvian R. Ray and Hillol Kargupta Department of Computer Science University of Illinois at Urbana-Champaign Urbana, Illinois 61801
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/thadani.ps.gz, 19940722 Constructing Functional Models of a Device from its Structural Description By Sunil Thadani, Ph.D. The Ohio State University, 1994 B. Chandrasekaran, Adviser This work proposes a solution for a version of the device understanding problem. Several tasks involving reasoning about devices, such as
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/kolen.ps.gz, 19940722
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/kolen.thesis.ps.Z, 19940726
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/massone.plant_properties.ps.Z, 19940727 A Study of the Role of Plant Properties in Arm Trajectory Formation Lina L.E. Massone and Jennifer D. Myers Technical Report 2/94 Neural Information Processing Laboratory Northwestern University Lina L.E. Massone (massone@eecs.nwu.edu) is with the Department of Electrical Engineering & Computer Science
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/massone.arm_model.ps.Z, 19940727 A Neural Network Model of an Anthropomorphic Arm Lina L.E. Massone and Jennifer D. Myers Technical Report 1/94 Neural Information Processing Laboratory Northwestern University Lina L.E. Massone (massone@eecs.nwu.edu) is with the Department of Electrical Engineering & Computer Science and the Biomedical
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/french.context-biasing.ps.Z, 19940727 (To appear in the Proceedings of the 16th Annual Cognitive Science Society Conference) Dynamically constraining connectionist networks to produce distributed, orthogonal representations to reduce catastrophic interference Robert M. French Willamette University, Salem, OR 97301 french@willamette.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/baldi.delays1.ps.Z, 19940727 1 How Delays Affect Neural Dynamics and Learning Pierre Baldi * Jet Propulsion Laboratory California Institute of Technology Pasadena, CA 91109 Amir Atiya Department of Computer Engineering Cairo University Giza, Egypt
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR36.ps.gz, 19940801 Low-Cost Checkpointing and Failure Recovery in Mobile Computing Systems Ravi Prakash and Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210. e-mail: fprakash, singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/baldi.delays2.ps.Z, 19940802 -2.5 -2 -1.5 -1 -0.5 0.5 1 1.5 2 200 400 600 800 1000 1200 1400 u t Fig. 1 "4_neuron_ring" "5_neuron_ring" -1.5 -1 -0.5 0.5 1 1.5 2 50 100 150 200 250 300 u t Fig. 2 'neuron_1' 'neuron_2' 'neuron_3' 'neuron_4' 1 23 4 5TTTT15213243T54fig. 4a Layer 1Layer 2Layer 3++-fig. 4b
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR42.ps.gz, 19940802 A Hierarchically-Connected Multiprocessor Jeffrey D. Martens The Ohio State University Department of Computer and Information Science Columbus, Ohio 43210-1277 (614) 292-1932 martens@cis.ohio-state.edu May 1, 1993 Revision of June 5, 1994 This work was presented as a poster at the 1994 Scalable
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jabri.ppap.ps.Z, 19940802 1 Practical Performance and Credit Assignment Efficiency of Analog Multi-layer Perceptron Perturbation Based Training Algorithms Marwan A. Jabri Systems Engineering and Design Automation Laboratory Sydney University Electrical Engineering NSW 2006 Australia marwan@sedal.su.oz.au SEDAL Technical Report
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/SanjayGupta.ps.gz, 19940803 DO WE KNOW IT ALL Whenever our ignorance is revealed, We say now the vacuum is filled, And then we claim, we know, All that is there to know. What new soul there can be Now that so much has been. Everything and everyone must be, A product of all that has been. And yet, here is a simple fact, We forget,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/alpaydin.road-distance.ps.Z, 19940807 FBE-IE-11/94-14 PARAMETRIC DISTANCE METRICS VS. NONPARAMETRIC NEURAL NETWORKS FOR ESTIMATING ROAD TRAVEL DISTANCES ETHEM ALPAYDIN _I. KUBAN ALTINEL NECAT_I ARAS A>=gustos 1994 August 1994 Fen Bilimleri Enstit us u Institute for Graduate Studies in Science and Engineering Bo>=gazi ci University, Bebek,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR30.ps.gz, 19940809 Skeletons and Techniques for the Systematic Development of Constraint Logic Programs Technical Report OSU-CISRC-6/94-TR30 Spiro Michaylov Department of Computer and Information Science, The Ohio State University, 228 Bolz Hall, 2036 Neil Avenue Mall, Columbus, OH 43210-1277, U.S.A.,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR31.ps.gz, 19940809 Repeated Redundant Inequalities in Constraint Logic Programming Technical Report OSU-CISRC-6/94-TR31 Spiro Michaylov Department of Computer and Information Science, The Ohio State University, 228 Bolz Hall, 2036 Neil Avenue Mall, Columbus, OH 43210-1277, U.S.A., Phone: +1 (614) 292 6377 FAX: +1 (614)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR43-DIR/p3trp1.ps.gz, 19940810 1 Synchronization and Desynchronization in a Network of Locally Coupled Wilson-Cowan Oscillators Shannon Campbell and DeLiang Wang Department of Physics Laboratory for Artificial Intelligence Research, Department of Computer and Information Science and Center for Cognitive Science The Ohio State
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR43-DIR/p3trp4.ps.gz, 19940811 41 Time Addition Sign House Tree Truck Helicopter GS Fig. 11
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pluto.imse.ps.Z, 19940811 Cross-Validation Estimates IMSE Mark Plutowski Department of Computer Science and Engineering and Institute for Neural Computation University of California, San Diego Shinichi Sakata Department of Economics University of California, San Diego Halbert White Department of Economics and Institute for
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR43-DIR/p3trp2.ps.gz, 19940811 37 Time x-activity Fig. 7
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR43-DIR/p3trp3.ps.gz, 19940811 38 0.02 0.04 0.06 0.08 0.1 x Nullclines and Triggering Region 0.02 0.04 0.06 0.08 0.1 y Fig. 8 39 Time 2 1 GS Fig. 9 40 A B C E F Fig. 10 D
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/gaskell.thesis.ps.Z, 19940811 Spoken Word Recognition: A Combined Computational and Experimental Approach Mark Gareth Gaskell Birkbeck College University of London Thesis submitted for the degree of Doctor of Philosophy March 1994 2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/grino.sysid.ps.Z, 19940812 NONLINEAR SYSTEM IDENTIFICATION USING ADDITIVE DYNAMIC NEURAL NETWORKS. R. GRI~N O Institut de Cibern etica (UPC-CSIC), Diagonal 647, 08028-Barcelona, Spain. E-mail: grino@ic.upc.es
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zimmer.comparison.ps.Z, 19940816 IWK 94, Ilmenau, Germany September 27 - 30, 1994 Comparing World-Modelling Strategies for Autonomous Mobile Robots Uwe R. Zimmer & Ewald von Puttkamer University of Kaiserslautern - Computer Science Department - Research Group Prof. E. v. Puttkamer 67663 Kaiserslautern - Germany Phone: 49 631 205 2624 -
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/burgess.hbtnn.ps.Z, 19940816 Burgess, Recce & O'Keefe. Spatial Models of the Hippocampus, 8 the monkey produce long-lasting memory impairment in the visual and tactual modalities, J. Neuroscience, 13: 2430-2451. * Traub, R.D., Miles, R., Muller, R.U. and Gulyas, A.I., 1992, Functional organization of the hippocampal CA3 region:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/neumerkel.realtimempc.ps.Z, 19940816 The 3rd IEEE Conference on Control Applications 24.-26. August 1994, The University of Strathclyde, Glasgow, Scotland, UK 1 Real-Time Application of Neural Model Predictive Control for an Induction Servo Drive D. Neumerkel, J. Franz L. Kr ger, A. Hidiroglu Daimler-Benz AG, Forschung Systemtechnik
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zimmer.alice.ps.Z, 19940816 TSRPC '94, Leeuwenhorst, The Netherlands, June 24-26, 1994 ALICE Topographic Exploration, Cartography and Adaptive Navigation on a Simple Mobile Robot Pascal Lef vre, Andreas Pr & Uwe R. Zimmer University of Kaiserslautern - Computer Science Department - Research Group Prof. E. v. Puttkamer P.O. Box
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/webber.self-org.ps.Z, 19940818 Network: Computation in Neural Systems 5(4), November 1994 Self-organisation of transformation-invariant detectors for constituents of perceptual patterns Chris J.S. Webber Departments of Physiology, Engineering & Physics, University of Cambridge Now at: Pattern Processing Theory, Defence Research
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/koncar.natural_language_translation.ps.Z, 19940819 A Natural Language Translation Neural Network Nenad KONCAR Imperial College of Science, Technology and Medicine, London, UK N.Koncar@doc.ic.ac.uk Dr. Gregory GUTHRIE Maharishi International University, Fairfield, Iowa, USA guthrie@miu.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shultz.pronouns.ps.Z, 19940819 In S. J. Hanson, T. Petsche, M. Kearns, & R. L. Rivest (Eds.) (1994). Computational learning theory and natural learning systems, Vol. 2: Intersection between theory and experiment (pp. 347-362). Cambridge, MA: MIT Press. A Connectionist Model of the Learning of Personal Pronouns in English Thomas R.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/bradtke.thesis.ps.Z, 19940819 Incremental Dynamic Programming for On-Line Adaptive Optimal Control Steven J. Bradtke CMPSCI Technical Report 94-62 August 1994 NOTE: This thesis is available via anonymous ftp from the site ftp.cs.umass.edu in the directory pub/techrept/techreport/1994. INCREMENTAL DYNAMIC PROGRAMMING FOR ON{LINE
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bradtke.rlforlq.ps.Z, 19940819 Adaptive Linear Quadratic Control Using Policy Iteration Steven J. Bradtke, B. Erik Ydstie, and Andrew G. Barto CMPSCI Technical Report 94-49 June 1994 NOTE: This paper is available by anonymous ftp from the site ftp.cs.umass.edu in the directory pub/techrept/techreport/1994. Adaptive linear quadratic
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/campbell.wc_oscillators.ps.Z, 19940819 OSU-CISRC-8/94-TR43 1 Synchronization and Desynchronization in a Network of Locally Coupled Wilson-Cowan Oscillators Shannon Campbell and DeLiang Wang Department of Physics Laboratory for Artificial Intelligence Research, Department of Computer and Information Science and Center for Cognitive Science
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/refs.ps.gz, 19940820 118 VI LIST OF REFERENCES Agre, P. E. (1993). The symbolic worldview: Reply to Vera and Simon. Cognitive Science, 17(1):61-69. Agre, P. E. and Chapman, D. (1986). Pengi: An implementation of a theory of activity. In Proceedings of the Sixth National Conference on Artificial Intelligence, pages 268- 272.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/ch4.ps.gz, 19940820 49 CHAPTER IV IV AN EVOLUTIONARY APPROACH TO ADAPTIVE BEHAVIOR One thing that connectionist networks have in common with brains is that if you open them up and peer inside, all you see is a big pile of goo. Michael Mozer and Paul Smolensky1 4.1 Introduction A subsumptive system, such as that of Figure 6
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/abstract.ps.gz, 19940820 1 THE EVOLUTION OF COMMUNICATION IN ADAPTIVE AGENTS By Gregory M. Saunders, Ph. D. The Ohio State University, 1994 Professor Jordan B. Pollack, Adviser The field of adaptive behavior holds that higher-level cognitive skills arise from the more primitive ability of an agent to adapt to its environment.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/ch1.ps.gz, 19940820 1 CHAPTER I I INTRODUCTION
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/ch3.ps.gz, 19940820 35 CHAPTER III III A CONNECTIONIST APPROACH TO ADAPTIVE BEHAVIOR ...how information is represented can greatly affect how easy it is to do different things with it. David Marr1 3.1 Introduction In this chapter, I present my first approach to adaptive behavior. Using Chandrasekaran and Josephson s
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/cover.ps.gz, 19940820 J. B. Pollack B. Chandrasekaran F. Zhao Dissertation Committee: THE EVOLUTION OF COMMUNICATION IN ADAPTIVE AGENTS DISSERTATION Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the Graduate School of The Ohio State University By Gregory Morris Saunders, B.S.,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/ch5.ps.gz, 19940820 74 CHAPTER V V THE EVOLUTION OF COMMUNICATION stem from a picture of a program constructed of cooperating modules that talk to each other. While this may be a reasonable metaphor in some ways, anyone who has actually written such a program knows that talking
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/ch6.ps.gz, 19940820 109 CHAPTER VI VI REMARKS Suppose, for example, that we adopt the intentional stance toward bees, and note with wonder that they seem to know that dead bees are a hygiene problem in a hive; when a bee dies its sisters recognize that it has died, and believing that dead bees are a health hazard and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/saunders_greg/ch2.ps.gz, 19940820 10 CHAPTER II II BACKGROUND is concerned only with science; not with engineering. In particular, it is concerned with the relationship of computational neuroscience to cognitive science. It is not concerned with any attempt to create intelligent artefacts that employ
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/duch.fsm.ps.Z, 19940823 1. Introduction In this paper a model of a universal adaptive system based on multidimensional localized functions is presented. This model facilitates the classification-approximation and employs a new way of knowledge representation by storing complex and fuzzy facts directly in the feature space. At
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR46.ps.gz, 19940823 Tracing The Missing Information Neelam Soundararajan Computer and Information Science The Ohio State University Columbus, OH 43210, USA. e-mail: neelam@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/prechelt.eval.ps.Z, 19940826 A Study of Experimental Evaluations of Neural Network Learning Algorithms: Current Research Practice Lutz Prechelt (prechelt@ira.uka.de) Fakult at f ur Informatik Universit at Karlsruhe 76128 Karlsruhe, Germany +49/721/608-4068, Fax: +49/721/694092 Technical Report 19/94 August 24, 1994
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr47-94-trip-multicast.ps.Z, 19940827 A Trip-based Multicasting Model in Wormhole-routed Networks with Virtual Channels Yu-Chee Tseng, Dhabaleswar K. Panda, and Ten-Hwang Lai Technical Report OSU-CISRC-8/94-TR47 A preliminary version of this paper was presented in International Parallel Processing Symposium (IPPS '93). Manuscript is under
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR47.ps.gz, 19940827 A Trip-based Multicasting Model in Wormhole-routed Networks with Virtual Channels Yu-Chee Tseng, Dhabaleswar K. Panda, and Ten-Hwang Lai Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 Tel: (614)292-5813, Fax: (614)292-2911 Email: ftseng, panda,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/buckingham.velocity.ps.Z, 19940903 In Proceedings of the Sixteenth Annual Conference of the Cognitive Science Society (pp. 72-77). Hillsdale, NJ: Erlbaum. A Connectionist Model of the Development of Velocity, Time, and Distance Concepts David Buckingham Thomas R. Shultz Department of Psychology Department of Psychology McGill University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/floreen.hopfield.ps.Z, 19940903 Complexity Issues in Discrete Hopfield Networks Patrik Flor een and Pekka Orponen University of Helsinki, Department of Computer Science P. O. Box 26, FIN-00014 University of Helsinki, Finland
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/henderson.thesis.ps.Z, 19940903 DESCRIPTION BASED PARSING IN A CONNECTIONIST NETWORK James Brinton Henderson A Dissertation in Computer and Information Science Presented to the Faculties of the University of Pennsylvania in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy 1994 Mitchell Marcus Supervisor
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr20-94-msgord.ps.Z, 19940906 Impact of Message-Ordering in Wormhole-Routed Multicomputers Dhabaleswar K. Panda and Vibha Dixit-Radiya Technical Report OSU-CISRC-9/94-TR20 A preliminary version of this paper was presented at Scalable High Performance Computing Conference (SHPCC '94). Manuscript is under review for Journal of
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR20.ps.gz, 19940914 Impact of Message-Ordering in Wormhole-Routed Multicomputers Dhabaleswar K. Panda and Vibha Dixit-Radiya Technical Report OSU-CISRC-9/94-TR20 A preliminary version of this paper was presented at Scalable High Performance Computing Conference (SHPCC '94). Manuscript is under review for Journal of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/massone.colliculus.ps.Z, 19940916 Local Dynamic Interactions in the Collicular Motor Map: A Neural Network Model Lina L. E. Massone and Tony Khoshaba Technical Report 4/94 Neural Information Processing Laboratory Northwestern University Lina L. E. Massone (massone@eecs.nwu.edu) is with the Department of Electrical Engineering & Computer
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR53.ps.gz, 19940930 Global Reduction in Wormhole k-ary n-cube Networks with Multidestination Exchange Worms1 Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: panda@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr53-94-reduction.ps.Z, 19941001 Global Reduction in Wormhole k-ary n-cube Networks with Multidestination Exchange Worms Dhabaleswar K. Panda Technical Report OSU-CISRC-8/94-TR53 Manuscript has been submitted to International Parallel Processing Symposium (IPPS '95). 1 Global Reduction in Wormhole k-ary n-cube Networks with
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR51.ps.gz, 19941003 Path Failure in Cylinderical Mesh Networks y J. Ramachandran Computer and Information Sciences Ohio State University Columbus, Ohio, 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/shultz.balance-ml.ps.Z, 19941004 MODELING COGNITIVE DEVELOPMENT 33 1 2-5 6-9 10-20 2 4 6 75th Last Torque Difference Error Epoch Figure 10. Mean errors on balance scale test problems at four torque difference levels. MODELING COGNITIVE DEVELOPMENT 32 200150100500 2 4 6 8 10 12 1 2-5 6-9 10-20 Epoch Error Torque difference 200150100500
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fels.glove-talkII.ps.Z, 19941004 Glove-TalkII: Mapping Hand Gestures to Speech Using Neural Networks { An Approach to Building Adaptive Interfaces by S. Sidney Fels A thesis submitted in conformity with the requirements for the degree of doctor of philosophy Graduate Department of Computer Science University of Toronto Toronto,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR54.ps.gz, 19941005 On the Synchronization Mechanisms in Distributed Shared Memory Systems Mahendra Ramachandran and Mukesh Singhal Department of Computer and Information Science The Ohio State University, Columbus, Ohio 43210-1277 email: framach,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/Rao_Roshan.ps.gz, 19941010 THESIS ABSTRACT THE OHIO STATE UNIVERSITY GRADUATE SCHOOL NAME: Roshan M. Rao QUARTER/YEAR: Autumn 1994 DEPARTMENT: Computer and Information Science DEGREE: M.S. ADVISER'S NAME: D. N. Jayasimha TITLE OF THESIS: Utilization Imbalance in Wormhole Routed Networks Wormhole routing is a popular switching
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/prechelt.bench.ps.Z, 19941014 Proben1 \| A Set of Neural Network Benchmark Problems and Benchmarking Rules Lutz Prechelt (prechelt@ira.uka.de) Fakult at f ur Informatik Universit at Karlsruhe 76128 Karlsruhe, Germany ++49/721/608-4068, Fax: ++49/721/694092 September 30, 1994 Technical Report 21/94
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR55.ps.gz, 19941014 Reverse Engineering of Legacy Code is Intractable Bruce W. Weide Wayne D. Heym Department of Computer and Information Science The Ohio State University Columbus, OH 43210 {weide,heym}@cis.ohio-state.edu Joseph E. Hollingsworth Department of Computer Science Indiana University Southeast New Albany, IN
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/meade.nonlinearodes.ps.Z, 19941014 SOLUTION OF NONLINEAR ORDINARY DIFFERENTIAL EQUATIONS BY FEEDFORWARD NEURAL NETWORKS Andrew J. Meade, Jr: and Alvaro A. Fernandez Rice University Department of Mechanical Engineering and Materials Science Houston, Texas, 77251-1892, USA Phone: (713) 527-8101 ext. 3590 email: meade@rice.edu To appear in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/huayang.nnstable.ps.Z, 19941101 Exponential Stability and Oscillation of Hopfield Graded Response Neural Network Hua Yang1, T.S.Dillon2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/plate.thesis.ps.Z, 19941101 Distributed Representations and Nested Compositional Structure by Tony A. Plate A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Graduate Department of Computer Science University of Toronto c Copyright by Tony Plate 1994 Distributed Representations and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/copelli.committee.ps.Z, 19941101 ON-LINE LEARNING IN THE COMMITTEE MACHINE Mauro Copelli and Nestor Caticha Instituto de F sica, Universidade de S~ao Paulo, CP 20516, 01498 S~ao Paulo, SP, Brazil e-mail : copelli@if.usp.br and nestor@if.usp.br October 11, 1994 Submitted to Journal of Physics A
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/cohen.thesis.ps.Z, 19941101 TEL - AVIV UNIVERSITY Faculty of Engineering Department of Electronics Physical Electronics Program Training Synaptic Delays in a Recurrent Neural Network. Thesis submitted towards the degree of "Master of Science" by Barak Cohen August 1994 TEL - AVIV UNIVERSITY Faculty of Engineering Department of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/murata.integralrep.ps.Z, 19941101 Function Approximation by Three-Layered Networks and Its Error Bounds \| An Integral Representation Theorem Noboru Murata METR 94-19 October 1994 Function Approximation by Three-Layered Networks and Its Error Bounds \| An Integral Representation Theorem Noboru Murata University of Tokyo METR 94-19,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/phatak.layered-cascor.ps.Z, 19941101 Connectivity and Performance Tradeoffs in the Cascade Correlation Learning Architecture D. S. Phatak Electrical Engineering Department State University of New York, Binghamton, NY 13902{6000 I. Koren Department of Electrical and Computer Engineering University of Massachusetts, Amherst, MA 01003
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR56.ps.gz, 19941102 Submitted to: Int. Conf. Computer Applications in Eng. and Medicine VoxelFlow: A Parallel Volume Rendering Method for Scientific Visualization Asish Law, Roni Yagel, and D.N. Jayasimha Department of Computer and Information Science The Ohio State University Columbus, Ohio {law, yagel,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schiff.bp_speedup.ps.Z, 19941110 Optimization of the Backpropagation Algorithm for Training Multilayer Perceptrons W. Schiffmann, M. Joost, R. Werner University of Koblenz Institute of Physics Rheinau 1 56075 Koblenz e-mail: evol@infko.uni-koblenz.de September 29, 1994 (First edition published in 1992) Contents 1 Introduction 3 2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/davisd.bayesinversion.ps.Z, 19941110 Solving Inverse Problems by Bayesian Iterative Inversion of a Forward Model with Applications to Parameter Mapping using SMMR Remote Sensing Data Daniel T. Davis, Zhengxiao Chen, Jenq-Neng Hwang, Leung Tsang Department of Electrical Engineering, FT-10 University of Washington Seattle, Washington 98195
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/chen.radial_approx.ps.Z, 19941114 Accepted for Publication by IEEE Transactions on Neural Networks. Approximation Capability to Functions of Several Variables, Nonlinear Functionals and Operators by Radial Basis Function Neural Networks Tianping Chen1 and Robert Chen2
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/abolfazlian.cocktail.ps.Z, 19941114 The Cocktail Party Listener A. R. Kian Abolfazlian Brian L. Karlsen Computer Science Department Aarhus University Ny Munkegade, Bldg. 540 DK-8000 Arhus C Denmark
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/keerthi.rl-survey.ps.Z, 19941114 A Tutorial Survey of Reinforcement Learn- ing S SATHIYA KEERTHI and B RAVINDRAN Department of Computer Science and Automation Indian Institute of Science, Bangalore e-mail: fssk,ravig@chanakya.csa.iisc.ernet.in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/chen.universal_approx.ps.Z, 19941114 Accepted for publication by IEEE Transactions on Neural Networks. Universal Approximation to Nonlinear Operators by Neural Networks with Arbitrary Activation Functions and Its Application to Dynamical Systems Tianping Chen1 and Robert Chen2
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR48.ps.gz, 19941116 Modulo Classes and Advice J. Ramachandran Computer and Information Sciences Ohio State University Columbus, Ohio, 43210
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR49.ps.gz, 19941116 Kolmogorov Complexity and Toda's Theorem1 J. Ramachandran Computer and Information Sciences Ohio State University Columbus, Ohio, 43210 1Please address correspondence to J. Ramachandran, BU CS Dept, 111 Cummington Street, Boston, MA 02215. ramachan@cs.bu.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/contents.ps.gz, 19941121 DYNAMIC RERESENTATION OF MUSICAL STRUCTURE By Edward Wilson Large, Ph.D. The Ohio State Universtiy 1994 Copyright by Edward W. Large 1994 ii LIST OF TABLES TABLE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . PAGE 1. Squared
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch3.ps.gz, 19941121 19 CHAPTER III A STUDY OF MUSIC PERFORMANCE AND IMPROVISATION This chapter describes an empirical study of the performance and improvisation of melodies by skilled pianists. The data is analyzed for two purposes. First, the improvisations are analyzed to determine the nature of structural relationships
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch6.ps.gz, 19941121 66 CHAPTER VI SYNCHRONIZATION TO COMPLEX SIGNALS The perception of beat and meter is a fundamental cognitive/perceptual ability. In humans, this ability enables apparently simple behaviors including tapping along with a tune, and very complex behaviors including the ability of skilled musicians to
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch2.ps.gz, 19941121 9 CHAPTER II SEQUENCE STRUCTURE AND TEMPORAL STRUCTURE IN MUSIC This chapter presents a background of issues in music cognition that relate to the models that will be developed in subsequent chapters. First, perceptual grouping and recursive recoding, or chunking, are considered from the perspective of
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch5.ps.gz, 19941121 51 CHAPTER V SEQUENCE PROCESSING AND TEMPORAL PROCESSING The RAAM network of the previous chapter did a good job of capturing the sequential structure of musical melodies. It represented sequences with long distance dependencies. It also generalized well enough to capture relative importance among
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch9.ps.gz, 19941121 113 CHAPTER IX IMPLICATIONS: MUSIC COGNITION AND BEYOND The goal of this dissertation has been to understand how complex, temporally structured sequences may be coded as patterns of activation in artificial neural networks. The domain of the studies reported here was music, and simulation results were
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch7b.ps.gz, 19941121 86 0.2 0.4 0.6 0.8 1 0.2 0.4 0.6 0.8 1 Bare Winding Number (q/p) Coupling Strength (h1) Figure 35: An empirical regime diagram for the phase-coupled model with .t .10= 87 0.2 0.4 0.6 0.8 1 0.2 0.4 0.6 0.8 1 Bare Winding Number (q/p) Coupling Strength (h1) Figure 36: An empirical regime diagram for the
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch7a.ps.gz, 19941121 78 CHAPTER VII MODELING BEAT PERCEPTION AS A DYNAMICAL SYSTEM The preceding chapter presented two dynamical systems, an event generator and an oscillator, and a way of coupling the two systems together, a set of delta rules. Examples of the behavior of the coupled system showed that the oscillator can
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch7c.ps.gz, 19941121 88 7.2.2 Period-Coupling In phase-coupled systems, the period of the driven oscillator is altered because its phase is perturbed in every cycle. When the effect of the driving signal is removed, even for one cycle, the driven oscillator reverts to its intrinsic period. When the driver returns, a number
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch7d.ps.gz, 19941121 91 0.2 0.4 0.6 0.8 1 0.2 0.4 0.6 0.8 1 Bare Winding Number (q/p0) Coupling Strength (h1) Figure 39: An empirical regime diagram for the period-coupled model with .t .05= 92 7.3 An Efficient Algorithm To create a state-space for studying the coupled system, it was necessary to assume that driver was
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch8.ps.gz, 19941121 94 CHAPTER VIII SOME EXPERIMENTS WITH THE OSCILLATOR MODEL Chapter VII studied the dynamical system that was created by coupling the oscillator of Chapter VI to an isochronous input signal. The behavior of the oscillator under the influence of coupling was interesting. The regime diagrams of Figures 34
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/refs.ps.gz, 19941121 121 IX LIST OF REFERENCES Abraham, R. H., & Shaw, C. D. (1992). Dynamics: The geometry of behavior (2nd ed.). Redwood City, CA: Addison-Wesley. Allen, P. E., & Dannenberg, R. B. (1989). Tracking musical beats in real time. In Proceedings of the 1990 International Computer Music Conference (pp. 140-143).
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch4.ps.gz, 19941121 34 CHAPTER IV COMPUTING REDUCED MEMORY REPRESENTATIONS 4.1 Connectionism and Reductionist Music Theory This chapter describes a model of sequence representation that is sensitive to structural relationships among events. More specifically, the model described here computes the relative importance of
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/large_ed/ch1.ps.gz, 19941121 1 CHAPTER I MENTAL REPRESENTATIONS FOR MUSIC 1.1 Introduction The problem of how the human brain perceives and represents complex, temporally structured sequences of events is central to cognitive science. The basic questions of temporal sequence processing recur throughout the study of human activity,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/budinich.ellipse.ps.Z, 19941123 1 On the Ordering Conditions for Self-Organising Maps Marco Budinich and John G. Taylor Centre for Neural Networks - King s College London ( Permanent address: Dip. di Fisica & INFN, Via Valerio 2, 34127 Trieste, Italy; e-mail: mbh@dfists.ts.infn.it)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/kangas.thesis.ps.Z, 19941123 On the Analysis of Pattern Sequences by Self-Organizing Maps Jari Kangas Helsinki University of Technology Laboratory of Computer and Information Science Rakentajanaukio 2 C, SF-02150, FINLAND Thesis for the degree of Doctor of Technology to be presented with due permission for public examination and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/desa.thesis.ps.Z, 19941123 Unsupervised Classification Learning from Cross-Modal Environmental Structure by Virginia Ruth de Sa Submitted in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy Supervised by Professor Dana H. Ballard Department of Computer Science College of Arts and Science University of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.spiking.ps.Z, 19941123 On the Computational Complexity of Networks of Spiking Neurons (Extended Abstract) Wolfgang Maass Institute for Theoretical Computer Science Technische Universitaet Graz Klosterwiesgasse 32/2 A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR57.ps.gz, 19941128 Micro-Architecture vs. Macro-Architecture Joseph E. Hollingsworth Department of Computer Science Indiana University Southeast New Albany, IN 47150 jholly@ius.indiana.edu Bruce W. Weide Department of Computer and Information Science The Ohio State University Columbus, OH 43210 weide@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR45.ps.gz, 19941128 Mathematical Foundations and Notation of RESOLVE Wayne D. Heym Timothy J. Long William F. Ogden Bruce W. Weide Department of Computer and Information Science The Ohio State University Columbus, OH 43210 {heym,long,ogden,weide}@cis.ohio-state.edu Technical Report OSU-CISRC-8/94-TR45 (Aug. 1994; slightly
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR58.ps.gz, 19941201 - 1 - Rapid Previewing via Volume-based Solid Modeling Naeem Shareef and Roni Yagel Department of Computer and Information Science The Ohio State University Columbus, OH 43210-1277
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/morciniec.ntup_bench.ps.Z, 19941207 The n-tuple Classifier: Too Good to Ignore Micha l Morciniec and Richard Rohwer Dept. of Computer Science and Applied Mathematics Aston University Birmingham, UK B4 7ET December 2, 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fry.maxmut.ps.Z, 19941207 Revised Paper (April 4, 1994) Title: Observer-Participant Models of Neural Processing Author: Robert L. Fry Organization: Johns Hopkins University/Applied Physics Laboratory Phone: (410) 792-5945 Email: robert_fry@jhuapl.edu Author Address: Johns Hopkins University/Applied Physics Laboratory Johns
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dogaru.osc_in_nnet.ps.Z, 19941207 Robust Oscillations and Bifurcations in Cellular Neural Networks Radu Dogaru , A.T. Murgan Electronics and Communications Department, Daniel Ioan Electrical Engineering Department,Technical University of Bucharest, Bd. Armata Poporului nr.1, Bucharest, Romania tel. +40-1-68317800 / ext 338, e-mail: radu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/babloyantz.comput_chaos.ps.Z, 19941207 Computation with chaos: A paradigm for cortical activity A. Babloyantz and C. Louren co Service de Chimie-Physique, Universit e Libre de Bruxelles CP 231 - Campus Plaine, Boulevard du Triomphe B-1050 Bruxelles, Belgium
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr59-94-packaging.ps.Z, 19941207 Designing Clustered Multiprocessor Systems under Packaging and Technological Advancements Debashis Basak and Dhabaleswar K. Panda Technical Report OSU-CISRC-1994-TR59 Manuscript has been submitted for review to Transactions of Parallel and Distributed Systems. A preliminary version of this paper has
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/eide.zisc.ps.Z, 19941207 An implementation of the Zero Instruction Set Computer (ZISC036) on a PC/ISA-bus card . Eide1), Th. Lindblad2), C.S. Lindsey, M. Minerskj ld, G. Sekhniaidze3), and G. Sz kely4) Royal Institute of Technology Department of Physics - Frescati, Stockholm, Sweden
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR59.ps.gz, 19941208 Designing Clustered Multiprocessor Systems under Packaging and Technological Advancements 1 Debashis Basak and Dhabaleswar K. Panda Department of Computer and Information Science Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR22.ps.gz, 19941212 A Necessary and Sufficient Condition for Deadlock-Free Wormhole Routing Loren Schwiebert and D. N. Jayasimha1 Department of Computer and Information Science The Ohio State University Columbus, OH 43210 1277 floren,jayasimg@cis.ohio-state.edu April 29, 1994 Revised: December 10, 1994 1Part of this work
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/baxter.thesis.ps.Z, 19941216 LEARNING INTERNAL REPRESENTATIONS Jonathan Baxter BSc.(Hons) December 13, 1994 A thesis to be submitted in fulfillment of the requirements of a degree of Doctor of Philosophy at The Flinders University of South Australia. Author's address: Discipline of Mathematics, Faculty of Science, The Flinders
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rohwer.ram_bayes.ps.Z, 19941216 ffl ffi Two Bayesian treatments of the n-tuple recognition method Richard Rohwer NCRG/4323 Neural Computing Research Group Technical Report No. NCRG/4323 May 1994 Neural Computing Research Group Dept. of Computer Science and Applied Mathematics Aston University Aston Triangle Birmingham B4 7ET UK Tel:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.robust.ps.Z, 19941223 Robust Reasoning: Integrating Rule-Based and Similarity-Based Reasoning Ron Sun The University of Alabama Department of Computer Science Tuscaloosa, AL 35487 rsun@cs.ua.edu December 22, 1994 To appear in: Artificial Intelligence (AIJ), 1995 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/barkai.local.ps.Z, 19941223 Local and Global Convergence of On-Line Learning N. Barkai1, H. S. Seung2, and H. Sompolinsky1;2 1Racah Institute of Physics and Center for Neural Computation, Hebrew University, Jerusalem 91904, Israel 2AT&T Bell Laboratories, 600 Mountain Ave., NJ 07974, USA October 24, 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sun.schema.ps.Z, 19941223 Schemas, Logics, and Neural Assemblies Ron Sun Department of Computer Science The University of Alabama Tuscaloosa, AL 35487 rsun@athos.cs.ua.edu To appear in: Applied Intelligence. Vol.5, No.2. 1995. Abstract To implement schemas and logics in connectionist models, some form of basic-level organization
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/meeden.thesis.ps.Z, 19941223 TOWARDS PLANNING: INCREMENTAL INVESTIGATIONS INTO ADAPTIVE ROBOT CONTROL Lisa A. Meeden Submitted to the faculty of the Graduate School in partial fulfillment of the requirements for the degree Doctor of Philosophy in the Department of Computer Science Indiana University August 1994 ii Accepted by the
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR60.ps.gz, 19941223 Bipartite Permutation Graphs with Application to the Minimum Buffer Size Problem Ten-Hwang Lai and Shu-Shang Wei Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 E-mail: lai@cis.ohio-state.edu September 23, 1994
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR50.ps.gz, 19950106 The Polynomial Time Function Hierarchy 1 2 J. Ramachandran Computer and Information Sciences Ohio State University Columbus, Ohio 43210 1This work was supported in part by NSF Grant CCR-8909071 2Part of this research was done when the author was a visitor at New Mexico State University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stein.mce.ps.Z, 19950113 A Review of Minimum Classi cation Error Training Yaakov Stein Efrat Future Technology Ltd. 23 HaBarzel St. Tel Aviv 69710, Israel 15 Jan. 1994
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stein.false.ps.Z, 19950113 False Alarm Reduction Techniques for ASR and OCR Yaakov Stein Efrat Future Technology Ltd. 23 HaBarzel St. Tel Aviv 69710, Israel 1 Dec. 1993
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR02.ps.gz, 19950113 Submitted to SIGGRAPH 95. Space Deformation using Ray Deflectors Yair Kurzion and Roni Yagel Department of Computer and Information Science The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR03.ps.gz, 19950117 Submitted to SIGGRAPH 95. Error-Bounded and Adaptive Image Reconstruction Raghu Machiraju, Edward Swan, and Roni Yagel Department of Computer and Information Science The Advanced Computing Center for the Arts and Design The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR44.ps.gz, 19950123 Optimizing Compilation of Linear Arithmetic in a Class of Constraint Logic Programs Technical Report OSU-CISRC-8/94-TR44 Spiro Michaylov Bill Pippin Department of Computer and Information Science, The Ohio State University, 395 Dreese Lab, 2015 Neil Avenue Mall, Columbus, OH 43210-1277, U.S.A., Voice:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bieler.fault_diagnosis.ps.Z, 19950127 International Conference on INTELLIGENT SYSTEM APPLICATION TO POWER SYSTEMS 1994, Montpellier, France EVALUATION OF DIFFERENT AI-METHODS FOR FAULT DIAGNOSIS IN POWER SYSTEMS K. Bieler H. Glavitsch ETH Z urich, Switzerland ETH Z urich, Switzerland 8092 Z urich 8092 Z urich Tel.:+411 632 41 87 Tel.:+411
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/shouval.thesis.ps.Z, 19950127 Formation and Organization of Receptive fields, with an input Environment Composed of Natural Scenes by Harel Shouval B.Sc Tel-Aviv Universityy 1987 M.S Weizmann Institute 1989 Thesis Submitted in partial fulfillment of the requirements for the Degree of Doctor of Philosophy in the Department of Physics
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zecchina.mln-wspace.ps.Z, 19950127 Weight Space Structure and Internal Representations : a Direct Approach to Learning and Generalization in Multilayer Neural Networks R emi Monasson and Riccardo Zecchinay INFN and Dipartimento di Fisica, P.le Aldo Moro 2, I-00185 Roma, Italy y INFN and Dip. di Fisica, Politecnico di Torino, C.so Duca
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dingankar.relcompact-class.ps.Z, 19950127 IEEE TRANS. ON CIRCUITS AND SYSTEMS-I: FUNDAMENTAL THEORY AND APPLICATIONS, JANUARY 1995 1 Classifiers on Relatively Compact Sets Irwin W. Sandberg and Ajit T. Dingankar
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thimm.gain.ps.Z, 19950127 The Interchangeability of Learning Rate and Gain in Backpropagation Neural Networks G. Thimm, P. Moerland, and E. Fiesler IDIAP P. O. Box 592 CH-1920 Martigny, Switzerland Electronic mail: Thimm@IDIAP.CH
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/wuertz.thesis.ps.Z, 19950127 Multilayer Dynamic Link Networks for Establishing Image Point Correspondences and Visual Object Recognition Dissertation zur Erlangung des Grades eines Doktors der Naturwissenschaften in der Fakult at f ur Physik und Astronomie der Ruhr-Universit at Bochum von Rolf P. W urtz aus Heidelberg Tag der
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/giraud.lorentz.ps.Z, 19950127 Lorentzian Neural Nets B.G.Giraud Service Physique Th eorique, DSM, C.E.Saclay, 91191 Gif/Yvette, France Alan Lapedes and Lon Chang Liu Theoretical Division, Los Alamos National Laboratory, 87545 Los Alamos, NM, USA J.C.Lemm Institut f ur Theoretische Physik I, Universit at M unster, 48149 M unster,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/chown.dissertation.ps.Z, 19950127 CONSOLIDATION AND LEARNING: A CONNECTIONIST MODEL OF HUMAN CREDIT ASSIGNMENT by Eric Lance Chown A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Computer Science and Engineering) in The University of Michigan 1994 Doctoral Committee: Professor
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/burgess.serial_order.ps.Z, 19950130 To be published in: Tesauro G, Touretzky D & Alspector J (eds.), Neural Information Processing Systems 7, Morgan Kaufmann, San Mateo CA (1995). A solvable connectionist model of immediate recall of ordered lists Neil Burgess Department of Anatomy, University College London London WC1E 6BT, England
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bernabe.art1chip.ps.Z, 19950201 1994 Conference on Neural Information Processing Systems (NIPS 94) Denver, Colorado, November 28 - December 1 A Real Time Clustering CMOS Neural Engine T. Serrano-Gotarredona, B. Linares-Barranco, and J. L. Huertas Dept. of Analog Design, National Microelectronics Center (CNM), Ed. CICA, Av. Reina
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/bodenhausen.thesis.ps.Z, 19950201 Automatic Structuring of Neural Networks for Spatio-Temporal Real-World Applications Zur Erlangung des akademischen Grades eines Doktors der Naturwissenschaften der Fakult t f r Informatik der Universit t Karlsruhe (Technische Universit t) vorgelegte Dissertation von Ulrich Bodenhausen aus Korbach Tag
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nowlan.nips95.ps.Z, 19950201 A Convolutional Neural Network Hand Tracker Steven J. Nowlan Synaptics, Inc. 2698 Orchard Parkway San Jose, CA 95134 nowlan@synaptics.com John C. Platt Synaptics, Inc. 2698 Orchard Parkway San Jose, CA 95134 platt@synaptics.com
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR04.ps.gz, 19950208 Distributed Dynamic Channel Allocation for Mobile Computing Ravi Prakash Niranjan G. Shivaratri Mukesh Singhal The Ohio State University NEC Systems Laboratory, Inc. The Ohio State University Columbus, OH 43210 Princeton, NJ 08540 Columbus, OH 43210 Extended Abstract Mobile computing has found increased
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/french.tandem-stm-ltm.ps.Z, 19950221 Interactive tandem networks and the sequential learning problem Robert M. French Center for Research on Concepts and Cognition Indiana University, Bloomington, IN 47408 french@cogsci.indiana.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/miller.rfs_and_maps.ps.Z, 19950221 1 Receptive Fields and Maps in the Visual Cortex: Models of Ocular Dominance and Orientation Columns Kenneth D. Miller1 To appear in: Models of Neural Networks III, E. Domany, J.L. van Hemmen, and K. Schulten, Eds. (Springer-Verlag, NY), 1995. An earlier and briefer version of this article appeared in
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sollich.linear_perc.ps.Z, 19950221 Learning in large linear perceptrons and why the thermodynamic limit is relevant to the real world Peter Sollich Department of Physics, University of Edinburgh Edinburgh EH9 3JZ, U.K. P.Sollich@ed.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kinouchi.linear.ps.Z, 19950221 On-line versus Off-line Learning in the Linear Perceptron: a Comparative Study Osame Kinouchi and Nestor Catichay Instituto de F isica, Universidade de S~ao Paulo Caixa Postal 20516, 01452-990 S~ao Paulo, SP, Brazil
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.nips7-rl.ps.Z, 19950221 Finding Structure in Reinforcement Learning Sebastian Thrun University of Bonn Department of Computer Science III R omerstr. 164, D-53117 Bonn, Germany E-mail: thrun@carbon.informatik.uni-bonn.de Anton Schwartz Dept. of Computer Science Stanford University Stanford, CA 94305 Email:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/krogh.ensemble.ps.Z, 19950221 To appear in: G. Tesauro, D. S. Touretzky and T. K. Leen, eds. Advances in Neural Information Processing Systems 7 MIT Press, Cambridge MA, 1995. Neural Network Ensembles, Cross Validation, and Active Learning Anders Krogh Nordita Blegdamsvej 17 2100 Copenhagen, Denmark Jesper Vedelsby Electronics
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fritzke.nips94.ps.Z, 19950221 To appear in: G. Tesauro, D. S. Touretzky and T. K. Leen, (eds.), Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, 1995. A Growing Neural Gas Network Learns Topologies Bernd Fritzke Institut f ur Neuroinformatik Ruhr-Universit at Bochum D-44780 Bochum Germany
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.nips7-chess.ps.Z, 19950221 Learning To Play the Game of Chess Sebastian Thrun University of Bonn Department of Computer Science III R omerstr. 164, D-53117 Bonn, Germany E-mail: thrun@carbon.informatik.uni-bonn.de to appear in: Advances in Neural Information Processing Systems 7 G. Tesauro, D. Touretzky, and T. Leen, eds., 1995
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.nips7-rules.ps.Z, 19950221 Extracting Rules from Artificial Neural Networks with Distributed Representations Sebastian Thrun University of Bonn Department of Computer Science III R omerstr. 164, D-53117 Bonn, Germany E-mail: thrun@carbon.informatik.uni-bonn.de to appear in: Advances in Neural Information Processing Systems 7 G.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/large.diss.ps.Z, 19950221 DYNAMIC RERESENTATION OF MUSICAL STRUCTURE By Edward Wilson Large, Ph.D. The Ohio State Universtiy 1994 Copyright by Edward W. Large 1994 ii LIST OF TABLES TABLE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . PAGE 1. Squared
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thrun.lifelong-learning.ps.Z, 19950221 Lifelong Robot Learning1 Sebastian Thrun2 and Tom M. Mitchell3 2 University of Bonn, Institut f ur Informatik III, R omerstr. 164, 53117 Bonn, Germany 3 School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sollich.imperf_learn.ps.Z, 19950221 Learning from queries for maximum information gain in imperfectly learnable problems Peter Sollich David Saad Department of Physics, University of Edinburgh Edinburgh EH9 3JZ, U.K. P.Sollich@ed.ac.uk, D.Saad@ed.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bisant.ribosome.ps.Z, 19950227 To appear in: Nucleic Acids Research, 1995. Identification of Ribosome Binding Sites in Escherichia coli Using Neural Network Models David Bisant Neuroscience Program (151 B) Stanford University Stanford, CA 94305 bisant@decatur.stanford.edu Jacob Maizel National Cancer Institute, FCRF Bldg 469 Rm 151,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR06.ps.gz, 19950228 Characterizing and Evaluating Performance Tradeoffs in Causal Multicasting in ATM Networks Frank Adelstein and Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210-1277 {frank,singhal}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tresp.effic_miss.ps.Z, 19950301 In: G. Tesauro, D. S. Touretzky and T. K. Leen, eds., "Advances in Neural Information Processing Systems 7", MIT Press, Cambridge MA, 1995. Efficient Methods for Dealing with Missing Data in Supervised Learning Volker Tresp Siemens AG Central Research Otto-Hahn-Ring 6 81730 M unchen Germany Ralph
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tresp.combining.ps.Z, 19950301 In: G. Tesauro, D. S. Touretzky and T. K. Leen, eds., "Advances in Neural Information Processing Systems 7", MIT Press, Cambridge MA, 1995. Combining Estimators Using Non-Constant Weighting Functions Volker Tresp and Michiaki Taniguchi Siemens AG, Central Research Otto-Hahn-Ring 6 81730 M unchen,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/large.reduced.ps.Z, 19950301 REDUCED MEMORY REPRESENTATIONS FOR MUSIC Edward W. Large Caroline Palmer Jordan B. Pollack The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dingankar.error-bounds.ps.Z, 19950301 A NOTE ON ERROR BOUNDS FOR APPROXIMATION IN INNER PRODUCT SPACES Ajit Dingankar and Irwin W. Sandberg Department of Electrical and Computer Engineering The University of Texas at Austin Austin, Texas 78712
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/thodberg.bayes-ard.ps.Z, 19950301 A Review of Bayesian Neural Networks with an Application to Near Infrared Spectroscopy Hans Henrik Thodberg The Danish Meat Research Institute Maglegaardsvej 2, DK-4000 Roskilde e-mail thodberg@nn.dmri.dk Revised version of Manuscript 1132E-part I, Feb 6, 1995
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/large.resonance.ps.Z, 19950301 RESONANCE AND THE PERCEPTION OF MUSICAL METER Edward W. Large John F. Kolen The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR52.ps.gz, 19950307 Multi-Phase Redistribution: A Communication-Efficient Approach to Array Redistributionz Technical Report OSU-CISRC-9/94-52 S. D. Kaushik1, C.-H. Huang1, J. Ramanujam2, and P. Sadayappan1 1Department of Computer and Information Science The Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fuller.scl.ps.Z, 19950308 Supervised Competitive Learning Thomas H. Fuller, Jr. and Takayuki D. Kimura, WUCS-93-45 Reprinted from Journal of Intelligent Material Systems and Structures (pages 232-246) March 1994 Department of Computer Science Washington University Campus Box 1045 One Brookings Drive St. Louis, MO 63130-4899 This
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gordon.extrapolation.ps.Z, 19950308 The Use of Cross-Validation in Neural Network Extrapolation of Forest Tree Growth C. Gordon Applied Mathematics University of the Witwatersrand E-mail: CHRIS@gauss.cam.wits.ac.za
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR07.ps.gz, 19950308 An Asymptotically Optimal Minimum Degree Ordering of Regular Grids B. Kumar, P. Sadayappan, C.-H. Huang Department of Computer and Information Science The Ohio State University, Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr41-94-synch_muldest.ps.Z, 19950309 Fast Barrier Synchronization in Wormhole k-ary n-cube Networks with Multidestination Worms Dhabaleswar K. Panda Accepted to be published in Journal of Future Generation Computer Systems (FGCS). A special issue on High Performance Computer Architecture consisting of Best 10 papers from International
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR41.ps.gz, 19950310 Fast Barrier Synchronization in Wormhole k-ary n-cube Networks with Multidestination Worms1 Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: panda@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR19.ps.gz, 19950316 Compiling Array Expressions for Efficient Execution on Distributed-Memory Machines Technical Report OSU-CISRC-4/94-19(Revised) S. K. S. Gupta, S. D. Kaushik, C.-H. Huang, and P. Sadayappan Department of Computer and Information Science The Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part4.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 26 ure 18, offers improved frequency attenuation in the stopband and has better transmittance in the passband than the bilinear kernel, providing superior approximation to the box shaped frequency response of the sinc
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part5.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 27 a b FIGURE 17: Reconstruction using the pre-accumulated bilinear voxel kernel (80 projections of 128 pixels each, 128x128 voxels, 2 iterations, l=0.6, error =0.34, computation time=17.1 sec). a) Reconstructed
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part1.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 17 pixel pi's bank of subpixels pik averages to pi's intensity. This is simply done by adding to each pik a correction value determined by the difference between the intensity of pi and the average of the estimated
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part3.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 25 a b FIGURE 14: a) Bilinear interpolation kernel. b) Voxel projection template of the bilinear interpolation kernel for a proiection angle of 45 . a b FIGURE 15: Reconstruction using the bilinear voxel kernel and no
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part8.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 34 K. Tanabe, "Projection method for solving a singular system," Numer. Math., vol. 17, pp. 203-214, 1971. J.H. Thrall, ed., Current Practice of Radiology. St. Louis, Mo: B.C. Decker, 1993. K.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part0.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 14 For estimation of the reconstruction error we use the normalized root mean squared error measure : (8) Here oi is the value of voxel vi in the original Shepp-Logan phantom. For error estimation we focus solely
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part2.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 23 at a projection angle of 45 . We generate the pre-accumulated projection template by first accumulating table entries along each row and subsequently accumulating the resulting table along each column. Figure 12b
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part6.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 29 tion factor to ensure proper scaling of the reconstruction image. The Gaussian1/2 kernel is particularly convenient since, for all practical purposes, its influence beyond the radius of 1.5 voxel widths is
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR12-DIR/Part7.ps.gz, 19950320 K. Mueller, R. Yagel, and J.F. Cornhill : Efficient and Accurate Implementation of ART 30 a b FIGURE 21: Reconstruction using the Gaussian1/2 voxel kernel and 5 fold pixel supersampling (40 projections of 128 pixels each, 128x128 voxels, 5 iterations, l=0.5, error =0.33, computation time=26.0 sec). a)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/mandal/thesis.ps.gz, 19950324 Efficient Distributed Shared Memory using Mapped Segmentation and Reusable Single-Assignment Variables By Manas Mandal, Ph.D. The Ohio State University, 1995 Prof. P. Sadayappan, Adviser This dissertation describes the design and evaluation of a Distributed Shared Memory (DSM) system based on two
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR13.ps.gz, 19950331 ic e es i e . er s e e ie r i cie ce e es- e e s, r ce r iris . r si cis. i -s e.e s c c c c . c c c , , - c . c c , c , c c , c c - c c c . c . ., c , c , c c c . s: , c , c , , c , c , . Introduction A distributed computation consists of a set of processes that cooperate and compete to achieve a
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/theunissen.temporal.ps.Z, 19950331 Theunissen and Miller Temporal encoding in nervous systems 1 Preprint: to appear in the Journal of Computational Neuroscience 2 (2), 1995 Temporal Encoding in Nervous Systems: a Rigorous Definition FR D RIC THEUNISSEN* ft@cicada. berkeley.edu Department of Molecular and Cell Biology, 195 LSA, University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lenz.colorpca.ps.Z, 19950331 Unsupervised Filtering of Color Spectra Reiner Lenz, Mats Osterberg Image Processing Group, Dept. EE, Link oping University, S-58183 Link oping, Sweden, reiner@isy.liu.se, mats@isy.liu.se Jouni Hiltunen, Timo Jaaskelainen V ais al a Laboratory, Dept. Physics, University of Joensuu, FIN-80101
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR11.ps.gz, 19950331 1 CellFlow: A Parallel Rendering Scheme for Distributed Memory Architectures Asish Law and Roni Yagel Department of Computer and Information Science The Ohio State University Columbus, Ohio {law, yagel}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/casey.thesis.ps.Z, 19950331 UNIVERSITY OF CALIFORNIA, SAN DIEGO Computation In Discrete-Time Dynamical Systems A dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Mathematics by Michael Patrick Casey Committee in charge: Professor Michael H. Freedman, Chair Professor Peter
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hilario.neuro-symbolic95.ps.Z, 19950331 Neurosymbolic Integration: Unioed versus Hybrid Approaches M lanie Hilario, Yannick Lallement, Fr d ric Alexandre CUI - University of Geneva 24 rue G n ral-Dufour CH-1211 Geneva 4 hilario@cui.unige.ch CRIN-INRIA Lorraine BP 239 - Campus scientioque F-54506 Vand uvre-les-Nancy Cedex lallemen@loria.fr,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/marshall.context.ps.Z, 19950331 bdFebruary 1993; revised April 1994; accepted October 1994. In press, Neural Networks 8(3), 1995.ce Adaptive Perceptual Pattern Recognition by Self-Organizing Neural Networks: Context, Uncertainty, Multiplicity, and Scale JONATHAN A. MARSHALL Department of Computer Science University of North Carolina
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/fuller.thesis.ps.Z, 19950331 i WASHINGTON UNIVERSITY SEVER INSTITUTE OF TECHNOLOGY ___________________________________ ABSTRACT ___________________________________ SUPERVISED COMPETITIVE LEARNING: A TECHNOLOGY FOR PEN-BASED ADAPTATION IN REAL TIME by Thomas H. Fuller, Jr. ___________________________________________________________
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/irani.thesis.ps.Z, 19950331 Classifier evaluation and the use of algorithmic classifiers with expert system classifiers Erach. A. Irani. February 1993 Contents 1 Introduction 1 1.1 Classifiers and Expert System Classifiers : : : : : : : : : : : : : : : : : : : : 1 1.2 Expert Systems : : : : : : : : : : : : : : : : : : : : : : : :
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gaskell.phonrep.ps.Z, 19950331 A Connectionist Model.. 1 A Connectionist Model of Phonological Representation in Speech Perception M. Gareth Gaskell1, Mary Hare2 and William D. Marslen-Wilson1 1Centre for Speech and Language, Birkbeck College, University of London and 2Center for Research in Language University of California in San
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/7.3-appendixC.ps.gz, 19950404 APPENDIX C How Does the ACTI Model Measure Up Given the formal description in Chapter IV, the ACTI model will be analyzed using the check list developed in Appendix B to determine how comprehensive it is. Section C.1 presents this analysis. Subsequent sections illustrate how each of the prior models
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/3-chapter3.ps.gz, 19950404 CHAPTER III ACTI: Supporting Mental Models for Understandable Software This chapter provides an explanatory introduction to the ACTI model of software subsystems. The basic concepts of ACTI are introduced at an informal, intuitive level, using an extended code example written in RESOLVE (Section A.3).
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/1-chapter1.ps.gz, 19950404 CHAPTER I Introduction In interacting with the environment, with others, and with the artifacts of technology, people form internal, mental models of themselves and of the things with which they are interacting. These models provide predictive and explanatory power for understanding the interaction.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/6-chapter6.ps.gz, 19950404 CHAPTER VI Conclusions This chapter summarizes the research conducted for this dissertation and presents the conclusions drawn from it. It continues by presenting the contributions of this research to the field of computer science, and concludes with a discussion of future research directions. 6.1
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/7.1-appendixA.ps.gz, 19950404 APPENDIX A Previous Models Because the idea of formalizing the concept of software or of software development has been around for so long, there are many research efforts relevant to a new formal modeling attempt. The research approach followed in this dissertation is to start with five modern models"
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/8-bibliography.ps.gz, 19950404 Bibliography Robert C. Bogdan and Sari Knopp Biklen. Qualitative Research For Education. Allyn and Bacon, Boston, MA, second edition, 1992. Paolo Bucci, Joseph E. Hollingsworth, Joan Krone, and Bruce W. Weide. Implementing components in RESOLVE. ACM SIGSOFT Software Engineering Notes,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/7.2-appendixB.ps.gz, 19950404 APPENDIX B Evaluating the Comprehensiveness of a Software Model Given the collection of previous models described in Appendix A, the next step is to devise an operational means of determining how comprehensive" each is\|the extent to which it addresses the intuitive notions about software construction
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/0-frontmatter.ps.gz, 19950404 A Formal Model of Software Subsystems By Stephen Hilary Edwards, Ph.D. The Ohio State University, 1995 Dr. Bruce W. Weide, Adviser People form internal mental models of the things they interact with in order to understand those interactions. This psychological insight has been used by the human-computer
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/5-chapter5.ps.gz, 19950404 CHAPTER V An Extended ACTI Example This chapter provides an extension of the running Partial Map example introduced in Chapter III, to illustrate some of the more advanced aspects of ACTI. It demonstrates the use of interpretation mappings between abstract and concrete instances, and explains the
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/4-chapter4.ps.gz, 19950404 CHAPTER IV The ACTI Definition This chapter presents the formal definition of ACTI. For the reader interested in the development of ACTI, Appendices A through C document the relevant background material, the method used to develop it, its requirements, and brief comparisons with four existing
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR14-DIR/2-chapter2.ps.gz, 19950404 CHAPTER II Understanding Software: Mental Models This chapter examines mental models and the question of how programmers understand software. This examination leads to an indictment of conventional programming languages for failing to provide real aids to the formation of effective mental models of
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR23.ps.gz, 19950405 Measures of Message Latency for Wormhole Routed Networks Kant C. Patel and D. N. Jayasimha1 Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 1277 Email: fpatel, jayasimg@cis.ohio-state.edu Phone: (614) 292 6653 Fax: (614) 292 2911 1Part of this work was done
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR19.ps.gz, 19950417 Distributed Dynamic Channel Allocation for Mobile Computing: Lessons from Load Sharing in Distributed Systems Ravi Prakash and Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR18.ps.gz, 19950417 1 A LA-COMA Implementation of Parallel Volume Rendering Asish Law and Roni Yagel Department of Computer and Information Science The Ohio State University Columbus, Ohio {law, yagel}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR20.ps.gz, 19950418 Real-Time Communications in Wireless FDDI Networks Yibin Yang Ten-Hwang Lai Ming-Tsan Liu Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210-1277 E-mail: fyyang, lai, liug@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/saad.online.ps.Z, 19950420 On-Line Learning in Soft Committee Machines David Saad1 and Sara A. Solla2 1Department of Physics, University of Edinburgh, King's Buildings, Mayfield Road, Edinburgh EH9 3JZ, UK. 2CONNECT, The Niels Bohr Institute, Blegdamsdvej 17, Copenhagen 2100, Denmark. The problem of on-line learning in two-layer
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/casey.relaxing-symmetry.ps.Z, 19950420 Relaxing The Symmetric Weight Condition for Convergent Dynamics in Discrete-Time Recurrent Networks Mike Casey Department of Mathematics 0112 UC San Diego 9500 Gilman Dr. La Jolla, CA 92093-0112 E-mail: mcasey@ucsd.edu Technical Report INC-9504 Institute for Neural Computation University of California,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/markey.thesis.ps.Z, 19950420 THE SENSORIMOTOR FOUNDATIONS OF PHONOLOGY: A COMPUTATIONAL MODEL OF EARLY CHILDHOOD ARTICULATORY AND PHONETIC DEVELOPMENT Kevin L. Markey CU-CS-752-94 1994 Department of Computer Science University of Colorado at Boulder Campus Box 430 Boulder, Colorado 80309-0430 USA Any opinions, findings, and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/biehl.noisy.ps.Z, 19950420 Learning from Noisy Data: An Exactly Solvable Model Michael Biehl, Peter Riegler, and Martin Stechert Institut f ur Theoretische Physik, Universit at W urzburg, Am Hubland, D{97074 W urzburg, Germany Exact results are derived for the learning of a linearly separable rule with a single layer perceptron.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/salustowicz.evnn.ps.Z, 19950420 Diplomarbeit A Genetic Algorithm for the Topological Optimization of Neural Networks Rafa l Sa lustowicz Matr. Nr.: 127242 Technische Universit at Berlin Fachbereich 13 { Informatik Institut f ur Wissensbasierte Systeme (WBS) Aufgabensteller: Prof. Dr. E. Konrad Betreuer: Prof. Dr. D.E. Rumelhart
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR10.ps.gz, 19950421 Technical Report OSU-CISRC-3/95-TR10, Comp. & Info. Sci., 1995 1 Adaptive Simulation and Control of Variable-Structure Control Systems in Sliding Regimes Feng Zhao Department of Computer and Information Science The Ohio State University Columbus, OH 43210 E-mail: fz@cis.ohio-state.edu Vadim I. Utkiny
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR21.ps.gz, 19950424 Fast Broadcast and Multicast in Wormhole Multistage Networks with Multidestination Worms1 Dhabaleswar K. Panda and Rajeev Sivaram Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pan.purdue-tr-ee-95-12.ps.Z, 19950427 Linsker-type Hebbian Learning: A Qualitative Analysis On The Parameter Space Jianfeng Fengy Mathematical Department University of Rome La Sapienza" P. le A. Moro, 00185 Rome, Italy Hong Pan Vwani P. Roychowdhury School of Electrical Engineering 1285 Electrical Engineering Building Purdue University
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tresp.deficient.ps.Z, 19950427 In: Cowan, J. D., Tesauro, G., and Alspector, J., eds., Advances in Neural Information Processing Systems 6, San Mateo, CA, Morgan Kaufman, 1994. Training Neural Networks with Deficient Data Volker Tresp Siemens AG Central Research 81730 M unchen Germany tresp@zfe.siemens.de Subutai Ahmad Interval
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR40.ps.gz, 19950504 On Mapping Data and Computation for Parallel Sparse Cholesky Factorization Kalluri Eswar C.-H. Huang P. Sadayappan Department of Computer and Information Science The Ohio State University Columbus Ohio 43210
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr33-94-multidest.ps.Z, 19950505 Multidestination Message Passing Mechanism Conforming to Base Wormhole Routing Scheme Dhabaleswar K. Panda, Sanjay Singal, and Pradeep Prabhakaran Technical Report OSU-CISRC-6/94-TR33 A short version of this report has been published in Proceedings of Parallel Routing and Communication Workshop, May
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR33.ps.gz, 19950508 Multidestination Message Passing Mechanism Conforming to Base Wormhole Routing Scheme1 Dhabaleswar K. Panda, Sanjay Singal and Pradeep Prabhakaran Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR22.ps.gz, 19950509 Tech Report OSU-CISRC-3/95-TR22, Comp. & Info. Sci., Ohio State U., 1995 1 Spatial Aggregate: Theory and Application to Qualitative Physics Kenneth Yip Feng Zhao y May 8, 1995
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/morcego.mannbib.ps.Z, 19950509 Modular Artificial Neural Networks Bibliography Compilation Date: May, 1995 Compiled by: Bernardo Morcego Automatic Control and Computer Engineering Dept. Universitat Polit cnica de Catalunya c/ Pau Gargallo, 5 08021 Barcelona, Spain email: bernardo@esaii.upc.es Albus, J.S., A new approach to
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/casey.how-rnns-work.ps.Z, 19950509 How Discrete-Time Recurrent Neural Networks Work Mike Casey Department of Mathematics 0112 UC San Diego 9500 Gilman Dr. La Jolla, CA 92093-0112 E-mail: mcasey@ucsd.edu Technical Report INC-9503 Institute for Neural Computation University of California, San Diego 9500 Gilman Drive DEPT 0523 1 How
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR26.ps.gz, 19950510 A Timing-based Schema for Stabilizing Information Exchange Anish Arora David M. Poduska December 1994 Revised: March 1995
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/adelstein/abstract.ps.gz, 19950526 1 Network and Operating Systems Support for Real-Time Multimedia By Frank N. Adelstein, Ph.D. The Ohio State University, 1995 Dr. Mukesh Singhal, Adviser Multimedia systems place a high demand on the network in terms of bandwidth, maximum end-to-end delay, and delay variance. Because of the recent
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/adelstein/123.ps.gz, 19950526 1. Chapter I 1 CHAPTER I Introduction 1.1 Background and Motivations Multimedia applications require a high network bandwidth and also impose stringent time constraints on the network, such as constraints on the maximum tolerable delay and the variance of the delay. This thesis focuses on network and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/adelstein/456.ps.gz, 19950526 89 0. Chapter 4 1. Chapter 4 2. Chapter 4 3. Chapter 4 4. Chapter 4 90 104 Chapter IV Characterizing and Evaluating Performance Tradeoffs in Causal Multicasting in ATM Networks 4.1 Introduction Asynchronous Transfer Mode (ATM) networks are connection-oriented, cell-switched networks with very small
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/adelstein/forward.ps.gz, 19950526 Network and Operating Systems Support for Real-Time Multimedia DISSERTATION Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the Graduate School of The Ohio State University By Frank Nathan Adelstein, B.S., M.S., The Ohio State University 1995 Dissertation
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR23.ps.gz, 19950609 Efficient Extraction of Imperative Computation in Constraint Logic Programs Technical Report OSU-CISRC-5/95-TR23 Christopher J. Bailey-Kellogg Spiro Michaylov Department of Computer and Information Science, The Ohio State University, 395 Dreese Laboratory, 2015 Neil Avenue, Columbus, OH 43210-1277,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR24.ps.gz, 19950609 Time and Money: A Case Study in Systematic Development of Constraint Logic Programs Technical Report OSU-CISRC-5/95-TR24 Spiro Michaylov Iv an Ord o~nez Department of Computer and Information Science, The Ohio State University, 395 Dreese Lab, 2015 Neil Avenue, Columbus, OH 43210-1277, U.S.A., Voice: +1
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr25-95-collective.ps.Z, 19950620 Issues in Designing Efficient and Practical Algorithms for Collective Communication on Wormhole-Routed Systems Dhabaleswar K. Panda Technical Report OSU-CISRC-5/95-TR25 Accepted to be presented in Workshop on Challenges for Parallel Processing, International Conference on Parallel Processing (ICPP),
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR25.ps.gz, 19950621 Issues in Designing Efficient and Practical Algorithms for Collective Communication on Wormhole-Routed Systems1 Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: panda@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/schwiebert.ps.gz, 19950630 A Comprehensive Study of Communication in Distributed-Memory Multiprocessors By Loren Schwiebert, Ph.D. The Ohio State University, 1995 D. N. Jayasimha, Adviser This dissertation studies the problem of channel contention in distributed-memory multiprocessors. Our main contributions are on adaptive
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/martinez.forget.ps.Z, 19950705 A ROBUST BACKWARD ADAPTIVE QUANTIZER Dominique MARTINEZ(1;2) & Woodward YANG(2) (1) Laboratoire d'Analyse et d'Architecture des Syst emes LAAS - CNRS, 7 Av. du Col. Roche, 31077 Toulouse, France. (2) Harvard University Division of Applied Sciences 29 Oxford St., Cambridge, MA 02138, USA.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/brunel.spontaneous.ps.Z, 19950705 Global spontaneous activity and local structured (learned) delay activity in cortex Daniel J. Amit Racah Institute of Physics, Hebrew University, Jerusalem, and INFN, Sezione di Roma, Istituto di Fisica Universita di Roma, La Sapienza, Ple Aldo Moro, Roma and Nicolas Brunel INFN, Sezione di Roma,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/koehn.gann.ps.Z, 19950705 - 96 - Vita Philipp Koehn was born in Erlangen, Germany on August 1, 1971 as the second son of Sigrid and Johannes Koehn. He attended the Buechenbach-Nord elementary school and graduated from the Albert-Schweitzer-Gymnasium in 1990. Since 1990, he has studied at the University of Erlangen-Nuremberg
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wilson.recurrent.ps.Z, 19950705 Proceedings of the Fourth Australian Conference on Neural Networks (ACNN 93) 189-192 A Comparison of Hidden layer (h nodes) State vector (h nodes) 1 Input layer (n nodes) w w Output layer (n nodes) w Architectural Alternatives for Recurrent Networks William H. Wilson School of Computer Science and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/brunel.learning.ps.Z, 19950705 Learning internal representations in an attractor neural network with analogue neurons Daniel J. Amit1 and Nicolas Brunel INFN, Sezione di Roma, Istituto di Fisica Universita di Roma, La Sapienza, Ple Aldo Moro, Roma
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stiber.transhyst.ps.Z, 19950705 Submitted to Int. Conf. on Brain Processes, Theories and Models. W.S. McCulloch: 25 Years in Memoriam, Nov. 1995 Hysteresis and Asymmetric Sensitivity to Change in Pacemaker Responses to Inhibitory Input Transients Michael Stiber and Ricci Ieong Technical Report HKUST-CS95-29 June 1995 Department of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/stiber.transcomp.ps.Z, 19950705 Submitted to Neural Information Processing Systems: Natural and Synthetic, Nov./Dec. 1995 Responses to Transients in Living and Simulated Neurons Michael Stiber , Ricci Ieong , and Jos e P. Segundoy Technical Report HKUST-CS95-26 May 1995 Department of Computer Science The Hong Kong University of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pawelzik.switch.ps.Z, 19950705 Annealed Competition of Experts for a Segmentation and Classification of Switching Dynamics Klaus Pawelzik z , Jens Kohlmorgen y , Klaus-Robert M uller +y z Institut f ur Theoretische Physik and SFB 185 Nichtlineare Dynamik Universit at Frankfurt, 60054 Frankfurt/M., Germany y GMD{FIRST (German National
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.shape.ps.Z, 19950705 On the Relevance of the Shape of Postsynaptic Potentials for the Computational Power of Spiking Neurons Wolfgang Maass Berthold Ruf
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR27.ps.gz, 19950705 Shape Transformation in Space-Time Jinghuan Lu and Kikuo Fujimura Department of Computer and Information Science The Ohio State University 2015 Neil Avenue, Columbus, OH 43210-1277 flu,fujimurag@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/brunel.dynamics.ps.Z, 19950705 Dynamics of an attractor neural network converting temporal into spatial correlations Nicolas Brunel INFN, Sezione di Roma, Istituto di Fisica Universita di Roma, La Sapienza, Ple Aldo Moro, Roma
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mueller.switch_speech.ps.Z, 19950705 Analysis of Switching Dynamics with Competing Neural Networks Klaus-Robert M ullery yy, Jens Kohlmorgenyy and Klaus Pawelzikyyy, Non-members SUMMARY We present a framework for the unsupervised segmentation of time series. It applies to non-stationary signals originating from different dynamical systems
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/klaus.lcurve.ps.Z, 19950705 A Numerical Study on Learning Curves in Stochastic Multi-Layer Feed-Forward Networks K.-R. M ullery#+, M. Finkez, N. Muratay, K. Schulten+, S. Amariy METR 95-03 May 1995 y Dept. of Math. Engineering and Inf. Physics, University of Tokyo, Hongo 7-3-1, Bunkyo-ku, Tokyo 113, Japan. # GMD FIRST, Rudower
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.spiking-details.ps.Z, 19950705 Lower Bounds for the Computational Power of Networks of Spiking Neurons Wolfgang Maass Institute for Theoretical Computer Science Technische Universitaet Graz Klosterwiesgasse 32/2 A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at June 19, 1995
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/beyer.mappings.ps.Z, 19950705 Reflex Research Group for Adaptive Systems SET.AS On data-driven derivation of discrete mappings between finite spaces Uwe Beyer Frank Smieja Report number: 1995/6 On data-driven derivation of discrete mappings between finite spaces Uwe Beyer Frank Smieja German National Research Center for Information
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wilson.stability.ps.Z, 19950705 To appear in Proceedings of the Sixth Australian Conference on Neural Networks (ACNN 95) 142-145 Stability of Learning in Classes of The relationship to work by Mozer, , on induction of temporal structure, is briefly described in . Recurrent and Feedforward Networks In the research reported here,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/martinez.bar.ps.Z, 19950705 Generalized Boundary Adaptation Rule for minimizing r-th power law distortion in case of high resolution quantization Dominique MARTINEZ(y) & Marc M. VAN HULLE(z) (y) Laboratoire d'Analyse et d'Architecture des Syst emes (LAAS) - CNRS, 7 Av. du Col. Roche, 31077 Toulouse, France (z) Laboratorium voor
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mareschal.object_permanence.ps.Z, 19950705 1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/keat.invariant.ps.Z, 19950705 PAPER TO BE PRESENTED AT THE FOURTH INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS - ANN 95 CAMBRIDGE, UK, 26-28 JUNE 1995. INVARIANT OBJECT RECOGNITION WITH A NEUROBIOLOGICAL SLANT J. Keat, V. Balendran, K. Sivayoganathan, and A. Sackfield*. Manufacturing Automation Research Group, Department
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/koehn.encoding.ps.Z, 19950705 - 1 - Combining Genetic Algorithms and Neural Networks: The Encoding Problem A Thesis Presented for the Master of Science Degree The University of Tennessee, Knoxville Philipp Koehn December 1994 - 2 - Dedication For Claudine Acknowledgment I would like to thank my major professor, Dr. Bruce MacLennan
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/schwenk.nips7.ps.Z, 19950706 published in NIPS*7, (David S. Touretzky, Gerald S. Tesauro, and Todd K. Leen, eds.), MIT Press, 1995 Transformation Invariant Autoassociation with Application to Handwritten Character Recognition Holger Schwenk Maurice Milgram PARC Universit e Pierre et Marie Curie tour 66-56, boite 164 4, place
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR31.ps.gz, 19950713 A STABILIZED MATRIX SIGN FUNCTION ALGORITHM FOR SOLVING ALGEBRAIC RICCATI EQUATIONS JUDITH D. GARDINERy
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR32.ps.gz, 19950714 1 Predicting and Estimating Job Execution Times in Computing Systems Using Survival Analysis M.G.Sriram and Mukesh Singhal msriram@cis.ohio-state.edu, singhal@cis.ohio-state.edu Division of Medical Informatics and Department of Computer Information Science The Ohio State University DRAFT #2, May 31,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR30.ps.gz, 19950714 1 Technical Report: OSU-CISRC-6/95-TR30 Incremental Learning of Complex Temporal Patterns1 DeLiang Wang and Budi Yuwono Laboratory for AI Research, Department of Computer and Information Science and Center for Cognitive Science Department of Computer and Information Science The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1993/TR25.ps.gz, 19950714 Measures of the Potential for Load Sharing in Distributed Computing Systems M.G. Sriram and Mukesh Singhal. Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 September 15, 1993
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr29-94-hetero.ps.Z, 19950715 Architectural and Communication Issues in Designing Heterogeneous Parallel Systems with Optical Interconnection Ravi Prakash and Dhabaleswar K. Panda Technical Report OSU-CISRC-06/94-TR29 Manuscript under review for IEEE Transactions on Computers. A preliminary version of this paper has been presented
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1994/TR29.ps.gz, 19950719 Architectural and Communication Issues in Designing Heterogeneous Parallel Systems with Optical Interconnection Ravi Prakash Dhabaleswar K. Panda Department of Computer and Information Science The Ohio State University, Columbus, OH 43210. Tel:(614)-292-5199, Fax: (614)-292-2911 E-mail: fprakash,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/quartz.const.ps.Z, 19950725 The Neural Basis of Cognitive Development: A Constructivist Manifesto Steven R. Quartz1 and Terrence J. Sejnowksi 2 submitted to: Behavioral & Brain Sciences 1Computational Neurobiology Laboratory, and The Sloan Center for Theoretical Neurobiology, The Salk Institute for Biological Studies, PO Box 85800
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fry.maxent.ps.Z, 19950725 The Fifteenth International Workshop on MAXIMUM ENTROPY AND BAYESIAN METHODS July 31 - August 4, 1995 Rational neural models based on information theory Robert L. Fry The Johns Hopkins University/Applied Physics Laboratory Laurel, MD 20723 I. INTRODUCTION AND OVERVIEW Biological organisms which possess
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/gerl.cavity-rsb.ps.Z, 19950725 Replica Symmetry Breaking and the Kuhn-Tucker Cavity Method in simple and multilayer Perceptrons F. GERL1 and U. KREY2 1 Institut f ur Theoretische Physik der Universit at G ottingen, Bunsenstr. 9, D-30373 G ottingen 2 Institut f ur Physik II der Universit at Regensburg, Universit atsstr. 31, D-93040
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wolpert.unify.ps.Z, 19950728 Tue Jul 25 12:08:41 1995 1 To retrieve a copy of the paper "The Relationshop Between PAC, the Statistical Physics Framework, the Bayesian Framework, and the VC Framework", anonymous ftp to ftp.santafe.edu. The paper is in pub/dhw_ftp, as relating.frameworks.ps.Z. Alternatively, the paper appears in "The
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch5a.ps.gz, 19950802 79 CHAPTER V V Experiment Results of SAPI 5.1 Introduction The purpose of this chapter is to present the results of the experiments. The chapter opens with a brief discussion of the input, output, and modes of processing, a definition of what constitutes the processing time in the results, and a
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/abstract.ps.gz, 19950802 Semantic and Pragmatic Parsing based on Systemic Grammar and Layered Abduction By Julie Ann Hartigan, Ph.D. The Ohio State University, 1994 B. Chandrasekaran, Adviser John Josephson, Co-Adviser Many linguists claim that natural language understanding (NLU) is a layered process; each layer creates an
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch1LOF.ps.gz, 19950802 xv LIST OF FIGURES FIGURE PAGE 1. Abduction versus layered abduction. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2. Graphical view of layered abduction and top-down guidance for semantic and pragmatic interpretation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/cover.ps.gz, 19950802 B. Chandrasekaran J. Josephson R. Kasper D. Wang Approved by SEMANTIC AND PRAGMATIC PARSING BASED ON SYSTEMIC GRAMMAR AND LAYERED ABDUCTION DISSERTATION Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the Graduate School of The Ohio State University By Julie
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch1TOC.ps.gz, 19950802 vii TABLE OF CONTENTS DEDICATION . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii ACKNOWLEDGEMENTS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii VITA . . . . . . . . . . . . . . . .
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch7.ps.gz, 19950802 149 CHAPTER VII VII Future Work and Further Implications 7.1 Introduction What has been introduced in the previous six chapters is a computational model for natural language understanding that utilizes additional knowledge in the form of run-time and anticipatory top-down guidance. The system
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch4.ps.gz, 19950802 49 CHAPTER IV IVSAPI - A Semantic And Pragmatic Interpretation System 4.1 Introduction Chapter II presented layered classificatory abduction, top-down guidance and systemic grammar at a high level. The purpose of this chapter is to produce a more detailed and specific explanation of how these items can
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch6.ps.gz, 19950802 135 CHAPTER VI VI Discussion of Results 6.1 Introduction The purpose of this chapter is to give a detailed review of the performance of the system and to discuss the level to which it met its objectives. Chapter 5 presented the timing results on a sentence-by-sentence basis with no discussion of the big
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch1.ps.gz, 19950802 1 CHAPTER I I Introduction The abilities to understand and generate natural language are fundamental to human existence; it is what enables us to communicate with one another. This communication is vital for the dissemination of ideas, concepts, fantasies, and stories, as well as the propagation of news
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch5b.ps.gz, 19950802 91 5.5.1 Effects of Anticipatory Guidance Table 3 gives the processing times for sentence 2 to run under the various anticipatory levels. This sentence, just like sentence 1, displayed the expected result; as the anticipation level increases, the highly-likely phase time increases, the likely phase time
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch2.ps.gz, 19950802 13 CHAPTER II II Classification, Abduction and Systemic Grammar 2.1 Introduction Many researchers have proposed that NLU involves some form of abduction or explanation-based reasoning .
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch5f.ps.gz, 19950802 123 Figure 64: Processing speedup caused by increasing the level of anticipation for sentences 6-8, without run-time guidance. Figure 65: Processing speedup caused by increasing the level of anticipation for sentences 6-8, with run-time guidance. Levels of Anticipation S p e e d u p Levels of
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch5e.ps.gz, 19950802 115 5.11.2 Run-Time Guidance Effects This sentence is an example of the ideal situation. As already seen, the anticipatory guidance had the exact effect that was expected. Likewise, the run-time guidance has the exact effect that was expected; speedup occurs with run-time guidance. Figure 57: Processing
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch1LOT.ps.gz, 19950802 xiii LIST OF TABLES TABLE PAGE 1. Effects of anticipatory guidance on sentence 1. . . . . . . . . . . . . . . . . . . . . . . . . . . 84 2. Run-time guidance effects on sentence 1.. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 86 3. Effects of anticipatory guidance on sentence 2. . . . .
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch3.ps.gz, 19950802 35 CHAPTER III III A Survey of Related Works 3.1 Introduction The task of natural language understanding can be decomposed into many subtasks. The system implemented as part of this research performs semantic and pragmatic interpretation by way of an abductive strategy using context as a guide. This
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch5d.ps.gz, 19950802 107 This sentence performed completely as expected: the highly-likely phase took longer, the likely phase took less time, and the net result was that the overall processing decreased from one level to the next. This information is depicted graphically in Figures 50 and 51. Figure 50: Highly-likely and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch5c.ps.gz, 19950802 99 attained in the likely phase did not completely compensate for the additional time used in the highly-likely phase. The reason that the complete anticipatory level managed a slight speedup is that an additional logicogrammatical feature in the input triggered the necessity of an additional pragmatic
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/hartigan/ch8.ps.gz, 19950802 173 APPENDIX A I Example of the Pragmatic Stratum A.1 Introduction To better comprehend the organization, representation and type of information represented in a stratum, it may be useful to view an actual stratum. The vastness of the logicogrammatical stratum makes it difficult to display and discuss
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR28.ps.gz, 19950810 Visibility Computation on Reconfigurable Meshes Kikuo Fujimura Department of Computer and Information Science The Ohio State University 2015 Neil Avenue, Columbus, Ohio 43210-1277 E-mail: fujimura@cis.ohio-state.edu Phone: 614-292-6730 Fax: 614-292-2911
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR33.ps.gz, 19950815 Necessary and Sufficient Conditions on Information for Causal Message Ordering and Their Optimal Implementation Ajay D. Kshemkalyani IBM Corporation P. O. Box 12195 Research Triangle Park NC 27709 Mukesh Singhal Department of Computer and Information Science The Ohio State University 2015 Neil Avenue
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/amari.overtraining.ps.Z, 19950823 Asymptotic Statistical Theory of Overtraining and Cross-Validation S. Amari y, N. Muratay, K.-R. M ullery x, M. Finkez, H. Yang METR 95-06 August 1995 y Department of Mathematical Engineering and Infomation. Physics, University of Tokyo, Hongo 7-3-1, Bunkyo-ku, Tokyo 113, Japan. x GMD FIRST, Rudower
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/seung.integrator.ps.Z, 19950823 Linear Network Models of the Oculomotor Integrators H. S. Seung AT&T Bell Laboratories Murray Hill, NJ 07974 July 31, 1995
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/lu.multisieve.ps.Z, 19950823 Appeared in Proceedings of Forth International Conference on Artificial Neural Networks, pp.92-97, Churchill College, University of Cambridge, UK, 26-28 June 1995. A PARALLEL AND MODULAR MULTI-SIEVING NEURAL NETWORK ARCHITECTURE FOR CONSTRUCTIVE LEARNING B.-L. Lu 1, K. Ito 1;2, H. Kita 3, and Y.
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr21-95-min-muldest.ps.Z, 19950823 Fast Broadcast and Multicast in Wormhole Multistage Networks with Multidestination Worms Dhabaleswar K. Panda and Rajeev Sivaram Technical Report OSU-CISRC-4/95-TR21 1 Fast Broadcast and Multicast in Wormhole Multistage Networks with Multidestination Worms1 Dhabaleswar K. Panda and Rajeev Sivaram Dept.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR35.ps.gz, 19950825 1 Priority-Driven Ray Tracing Roni Yagel1 and John Meeker2 1Department of Computer and Information Science, The Ohio State University, 2auto des sys Inc., Columbus OH
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR36.ps.gz, 19950906 Alleviating Consumption Channel Bottleneck in Wormhole-Routed k-ary n-cube Systems 1 Debashis Basak and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email: fbasak,pandag@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr36-95-consumption.ps.Z, 19950906 Alleviating Consumption Channel Bottleneck in Wormhole-Routed k-ary n-cube Systems Debashis Basak and Dhabaleswar K. Panda Technical Report OSU-CISRC-9/95-TR36 Manuscript is under review for IEEE Transactions of Parallel and Distributed Systems. A preliminary version of this paper has appeared in IPPS
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR38.ps.gz, 19950907 Representation Inheritance: A Safe Form of White Box" Code Inheritance Stephen H. Edwards Dept. of Computer and Information Science The Ohio State University 395 Dreese Lab 2015 Neil Avenue Columbus, Ohio 43210{1277 Phone: (614) 292{5841 E-Mail: edwards@cis.ohio-state.edu URL:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR37.ps.gz, 19950913 Characterizing Observability and Controllability of Software Components Bruce W. Weide Stephen H. Edwards Wayne D. Heym* Timothy J. Long William F. Ogden Department of Computer and Information Science The Ohio State University 2015 Neil Avenue Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR39.ps.gz, 19950913 Using Abstraction Relations to Verify
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kanter.time_series.ps.Z, 19950915 Analytical study of time series generation by feed-forward networks I. Kanter, D. A. Kessler, A. Priel and E. Eisenstein Minerva Center and Department of Physics, Bar-Ilan University, Ramat-Gan 52900, Israel Generation of time series is studied analytically for a generalization of the Bit-Generator to
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR01.ps.gz, 19950915 A Consensus-Based Approach to Implementing Semaphores in a Distributed Environment Mahendra Ramachandran and Mukesh Singhal Department of Computer and Information Science The Ohio State University, Columbus, Ohio 43210-1277 email: framach,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/salinas.trans.ps.Z, 19950915 To appear in Journal of Neuroscience TRANSFER OF CODED INFORMATION FROM SENSORY TO MOTOR NETWORKS Emilio Salinas and L.F. Abbott Center for Complex Systems Brandeis University Waltham, MA 02254 emilio@eliza.cc.brandeis.edu abbott@binah.cc.brandeis.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/winkel.correlated-patterns.ps.Z, 19950915 Storing Block-wise Semantically Correlated Patterns in a Perceptron: Results from a Cavity Method J. O. WINKEL1 F. GERL2 U. KREY1 1 Institut f ur Physik II der Universit at Regensburg, Universit atsstr. 31, D-93040 F.R.G. 2 Institut f ur Theoretische Physik der Universit at G ottingen, Bunsenstr. 9,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/cozzio.thesis.ps.Z, 19950915 Diss. ETH No. 10991 THE DESIGN OF NEURAL NETWORKS USING A PRIORI KNOWLEDGE A dissertation submitted to the SWISS FEDERAL INSTITUTE OF TECHNOLOGY ZURICH for the degree of Doctor of Technical Sciences presented by Rico A. Cozzio-B eler dipl. Informatik-Ing., ETH, Zurich born July 6, 1965 citizen of Uster,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR34.ps.gz, 19950919 Helly-Type Theorems and Geometric Transversals1 Rephael Wenger2 INTRODUCTION A geometric transversal is an affine subspace of Rd , such as a point, line, plane or hyperplane, which intersects every member of a family of convex sets. Eduard Helly's celebrated theorem gives conditions for the members of a
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/tresp.miss_time.ps.Z, 19950921 Missing and Noisy Data in Nonlinear Time-Series Prediction Volker Tresp and Reimar Hofmann Siemens AG, Central Research 81730 Munich, Germany To be published in: Neural Networks for Signal Processing 5, B. Wilson et al., eds., IEEE Signal Processing Society, Piscataway, NJ, 1995.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maclennan.contformalsys.ps.Z, 19950921 Continuous Formal Systems: A Unifying Model in Language and Cognition Bruce J. MacLennan Computer Science Department University of Tennessee, Knoxville July 3, 1995 1 Introduction The idea of a calculus or discrete formal system is central to traditional models of language, knowledge, logic, cognition
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR40.ps.gz, 19950927 Search in Temporal Domains Kikuo Fujimura Department of Computer and Information Science The Ohio State University 2015 Neil Avenue, Columbus, OH 43210 USA Email: fujimura@cis.ohio-state.edu Phone: 614-292-6730 Fax: 614-292-2911
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/podolak.text2phon.ps.Z, 19950927 Phonematic translation of polish texts by the neural network A. Bielecki I. T. Podolak J. Wosiek Institute of Computer Science, Nawojki 11, Cracow, Poland and E. Majkut Institute of Polish Philology, Jagiellonian University Go l ebia 14{20, Cracow, Poland
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/dingankar.thesis.ps.Z, 19950927 ON APPLICATIONS OF APPROXIMATION THEORY TO IDENTIFICATION, CONTROL AND CLASSIFICATION by AJIT TRIMBAK DINGANKAR, B.Tech., M.S., M.S. DISSERTATION Presented to the Faculty of the Graduate School of The University of Texas at Austin in Partial Fulfillment of the Requirements for the Degree of DOCTOR OF
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR05.ps.gz, 19950928 TEMPORAL ANALYSIS OF LOAD IMBALANCE IN DISTRIBUTED COMPUTING SYSTEMS M.G. Sriram and Mukesh Singhal. Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210 January 20, 1995
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR43.ps.gz, 19951003 A Quasi-synchronous Algorithm for Checkpointing in Distributed Systems D. Manivannan and M. Singhal Department of Computer and Information Science, The Ohio State University, Columbus, OH 43210. email: fmanivann, singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR41.ps.gz, 19951003 Benefits of Processor Clustering in Designing Large Parallel Systems: When and How 1 D. Basak, D. K. Panda M. Banikazemi Dept. of Computer and Information Science Dept. of Electrical Engineering The Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR42.ps.gz, 19951003 Modeling and Analysis of Channel Transferability in Mobile Computing Environments Ravi Prakash and Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210, U.S.A. e-mail: fprakash,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr41-95-benefits_clustering.ps.Z, 19951004 Benefits of Processor Clustering in Designing Large Parallel Systems: When and How D. Basak, D. K. Panda, and M. Banikazemi Technical Report OSU-CISRC-10/95-TR41 1 Benefits of Processor Clustering in Designing Large Parallel Systems: When and How 1 D. Basak, D. K. Panda M. Banikazemi Dept. of Computer
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR44.ps.gz, 19951004 An Efficient Causal Ordering Algorithm for Mobile Computing Environments Ravi Prakash Dept. of Computer and Info. Science The Ohio State University Columbus, OH 43210, U. S. A. prakash@cis.ohio-state.edu Michel Raynal IRISA Campus de Beaulieu Rennes Cedex, France. michel.raynal@irisa.fr Mukesh Singhal
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR45.ps.gz, 19951012 A Low-overhead Recovery Technique Using Quasi-synchronous Checkpointing D. Manivannan Distributed Systems Research Group Comp. & Info. Science Dept. The Ohio State University Columbus, OH 43210 Mukesh Singhal Distributed Systems Research Group Comp. & Info. Science Dept. The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR46.ps.gz, 19951012 Distributed Dynamic Fault-Tolerant Channel Allocation for Mobile Computing Ravi Prakash Department of Computer and Information Science The Ohio State University Columbus, OH 43210. e-mail: prakash@cis.ohio-state.edu Niranjan G. Shivaratri 4 Independence Way NEC Systems Laboratory, Inc. Princeton, NJ
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR47.ps.gz, 19951019 Randomized Quick Hull R. Wengery October 18, 1995
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dingankar.tensor-products.ps.Z, 19951103 Invited paper at NOLTA'95, Las Vegas, Nevada, December 10{14, 1995 1 Network Approximation of Dynamical Systems Ajit T. Dingankar and Irwin W. Sandbergy IBM Corporation, Austin, TX 78758, U.S.A., ajit@austin.ibm.com y The University of Texas at Austin, TX 78712, U.S.A., sandberg@uts.cc.utexas.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/copelli.equivalence.ps.Z, 19951103 Equivalence Between Learning in Perceptrons with Noisy Examples and Tree Committee Machines Mauro Copelli , Osame Kinouchiy and Nestor Catichaz Instituto de F sica, Universidade de S~ao Paulo Caixa Postal 66318, 05389-970 S~ao Paulo, SP, Brazil
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jacobs.hme_gibbs.ps.Z, 19951103 Bayesian Inference in Mixtures-of-Experts and Hierarchical Mixtures-of-Experts Models With an Application to Speech Recognition Fengchun Peng Department of Mathematics and Statistics University of Nebraska, Lincoln Robert A. Jacobs Department of Brain and Cognitive Sciences University of Rochester
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/freeman.rbf1.ps.Z, 19951106 Learning and Generalisation in Radial Basis Function Networks J.A.S. Freeman D.Saad Department of Physics University of Edinburgh Edinburgh EH9 3JZ United Kingdom This is the correct version to appear in Neural Computation.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR50.ps.gz, 19951106 1 Multi-Frame Thrashless Ray Casting with Advancing Ray-Front Asish Law and Roni Yagel Department of Computer and Information Science The Ohio State University Columbus, Ohio
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR49.ps.gz, 19951106 Efficient Rasterization of Implicit Functions Torsten M ller and Roni Yagel Department of Computer and Information Science The Ohio State University Columbus, Ohio {moeller, yagel}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR48.ps.gz, 19951106 Real-Time Communications in FDDI-Based Mobile Networks Ten-Hwang Lai Yibin Yang Ming-Tsan Liu Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210-1277 E-mail: flai, yyang, liug@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/rosen.exp-rec-loss.ps.Z, 19951106 HOWGOOD WERE THOSE PROBABILITY PREDICTIONS THE EXPECTED RECOMMENDATION LOSS (ERL) SCORING RULE David B. Rosen Center for Biomedical Modeling Research University of Nevada, Reno Present address: Department of Medicine New York Medical College Valhalla, NY 10595 USA Internet: d.rosen@ieee.org (or
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR51.ps.gz, 19951113 Designing Clustered Multiprocessor Systems under Packaging and Technological Advancements 1 Debashis Basak and Dhabaleswar K. Panda Department of Computer and Information Science Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.noisy-spiking.ps.Z, 19951118 On the Computational Power of Noisy Spiking Neurons Wolfgang Maass Institute for Theoretical Computer Science, Technische Universitaet Graz Klosterwiesgasse 32/2, A-8010 Graz, Austria, e-mail: maass@igi.tu-graz.ac.at
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/abdi.sex-generalized.ps.Z, 19951204 A generalized autoassociator model for face processing 19 Weller, A.C., Romney, A.K. (1990). Metric scaling: Correspondence analysis. Newsbury Park (CA): Sage. Wilkinson, J.H. (1965). The algebraic eigenvalue problem. New York: Oxford University Press. 18 Abdi, Valentin & O'Toole Cottrell, G.W., &
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bernabe.art1-vlsi.ps.Z, 19951204 November 22, 1995 4:31 pm 1 A Real-Time Clustering Microchip Neural Engine Teresa Serrano-Gotarredona and Bernab Linares-Barranco Centro Nacional de Microelectr nica (CNM), Dept. of Analog Design, Ed. CICA, Av. Reina Mercedes s/n, 41012 Sevilla, SPAIN, Phone: 34-5-4239923, Fax: 34-5-4624506, E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/bernabe.art1-nn.ps.Z, 19951204 November 23, 1995 12:57 pm Page: 1 A Modified ART 1 Algorithm more suitable for VLSI Implementations Teresa Serrano-Gotarredona and Bernab Linares-Barranco National Microelectronics Center (CNM), Dept. of Analog Design, Ed. CICA, Av. Reina Mercedes s/n, 41012 Sevilla, SPAIN. Phone: 34-5-4239923, Fax:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/abdi.mathpsy.ps.Z, 19951204 Ref: Valentin, D., Abdi, H., O'Toole, A.J. (in press, 1996). Principal component and neural networks analyses of face images: Explorations into the nature of information available for classifying faces by sex. In C. Dowling, F.S. Roberts,P. Theuns, Progress in mathematical psychology. Hillsdale:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/xli.thinfilm.ps.Z, 19951204 AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA AAAA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dingankar.linear-functionals.ps.Z, 19951204 402 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS-I: FUNDAMENTAL THEORY AND APPLICATIONS, VOL. 42, NO. 7, JULY 1995 On Approximation of Linear Functionals on Lp Spaces Irwin W. Sandberg and Ajit Dingankar Department of Electrical and Computer Engineering The University of Texas at Austin Austin, Texas 78712
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/blume.oe_fam.ps.Z, 19951204 Optical Computing, Vol. 10, 1995 OSA Technical Digest Series (Optical Society of America, Washington, DC, 1995), p. 213-215, March 1995. Optoelectronic Fuzzy ARTMAP Processor Matthias Blume and Sadik C. Esener matthias@ucsd.edu sadik@ece.ucsd.edu University of California, San Diego Electrical and
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/blume.fam_arch.ps.Z, 19951204 matthias@ucsd.edu Submitted to Neural Networks August, 1995 An efficient mapping of Fuzzy ART onto a neural architecture Matthias Blume and Sadik C. Esener Department of Electrical and Computer Engineering University of California at San Diego, La Jolla, CA 92093
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR52.ps.gz, 19951208 Hybrid Algorithms for Complete Exchange in 2D Meshes N. S. Sundar D. N. Jayasimha D. K. Panda P. Sadayappan Dept. of Computer & Information Science The Ohio State University Columbus, OH 43210 (sundar,jayasim,panda,saday)@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR29.ps.gz, 19951208 Constructing Piecewise Linear Homeomorphisms of Simple Polygons Himanshu Gupta Rephael Wengery December 6, 1995
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/chng.thesis.ps.Z, 19951218 Applications of nonlinear filters with the linear-in-the-parameter structure Eng Siong CHNG THEUNIVERSITY OFEDINBURGH A thesis submitted for the degree of Doctor of Philosophy. The University of Edinburgh. - December 1995 -
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/parra.nips95.ps.Z, 19951218 Symplectic Nonlinear Component Analysis Lucas C. Parra Siemens Corporate Research 755 College Road East, Princeton, NJ 08540 lucas@learning.scr.siemens.com
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR54.ps.gz, 19951219 Multidestination Message Passing in Wormhole k-ary n-cube Networks with Base Routing Conformed Paths1 Dhabaleswar K. Panda, Sanjay Singal, and Ram Kesavan Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR55-DIR/3-chapter-3.ps.gz, 19951219 CHAPTER III Proof Rules The purpose of a system of proof rules is to establish, by method of formal proof (a purely syntactic method), the validity (see Definition 2.1, page 58) of a given assertive program. The typical situation is that a team of programmers has produced a program and its
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR55-DIR/6-bibliography.ps.gz, 19951219 Bibliography Harold Abelson, Gerald Jay Sussman, and Julie Sussman. Structure and Interpretation of Computer Programs. McGraw-Hill Book Company, 1985. Alan Baddeley. Working memory. Science, 255:556, 31 January 1992. Manfred Broy. Experiences with software specification and verification
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR55-DIR/2-chapter-2.ps.gz, 19951219 CHAPTER II Syntax and Semantics An assertive program is a computer program that not only gives the instructions to be followed by the computer when it executes the program, but also asserts, in the specification portions of the program, what is to be accomplished when the program is executed. An
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR55-DIR/5-chapter-5.ps.gz, 19951219 CHAPTER V Conclusion 5.1 Informal and Formal Indexed Methods We defined, in Chapter II, a semantics for a procedural, imperative programming language with specifications: a language of assertive programs. In Chapter IV, we proved the soundness and relative completeness of the indexed method for proving
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR53.ps.gz, 19951219 Comprehensive Low-overhead Process Recovery Based on Quasi-synchronous Checkpointing D. Manivannan and M. Singhal Distributed Systems Research Group, Department of Computer and Information Science, The Ohio State University, Columbus, OH 43210. E-mail: fmanivann,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR55-DIR/0-front-matter.ps.gz, 19951219 Computer Program Verification: Improvements for Human Reasoning By Wayne David Heym, Ph.D. The Ohio State University, 1995 Bruce W. Weide, Adviser To ably create or modify computer programs that behave according to specification, programmers find it necessary to reason about their programs' behavior. We
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR55-DIR/4-chapter-4.ps.gz, 19951219 CHAPTER IV Soundness and Relative Completeness 4.1 Soundness In Chapter I (page 7), we said that soundness of the formal proof system implies the truth of the correctness conjecture for every assertive program (i.e., program-withspecification) that can be transformed to a mathematical statement that is
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR55-DIR/1-chapter-1.ps.gz, 19951219 CHAPTER I Introduction Does this computer program do what it is supposed to do Is this program correct Does it contain any errors These are three of the possible ways of phrasing a question for which many people seek a reliable answer. That not everyone demands a good answer to this question is evidence
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1995/TR56.ps.gz, 19960102 1 Distributed-Memory 3D Rendering with Object Migration Asish Law and Roni Yagel Department of Computer and Information Science The Ohio State University Columbus, Ohio {law, yagel}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR01.ps.gz, 19960110 An Information System to Support Collaborative Brain-Tumor Research Sandra A. Mamrak, M.S., Ph.D. John Boyd, M.S. Iv an Ord o~nez, M.S. Sandra L. Cottingham, M.D., Ph.D. Allan J. Yates, M.D., Ph.D. Affiliation of the Authors: Department of Computer and Information Science and Department of Pathology The
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/turmon.thesis.ps.Z, 19960111 MICHAEL J. TURMON Cornell University Doctor of Philosophy ASSESSING GENERALIZATION OF FEEDFORWARD NEURAL NETWORKS A dissertation presented to the faculty of the graduate school of in partial fulfillment of the requirements for the degree of August 1995 c Michael J. Turmon 1995 ALL RIGHTS RESERVED
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/pearlmutter.vcdifn.ps.Z, 19960111 VC Dimension of an Integrate-and-Fire Neuron Model Anthony M. Zador Barak A. Pearlmuttery To appear (1996) in Neural Computation 8(3)
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kolen.wgtxport.ps.Z, 19960111 Back-Propagation Without Weight Transport John F. Kolen and Jordan B. Pollack Laboratory for AI Research Department of Computer and Information Sciences The Ohio State University Columbus, OH 43210 kolen-j@cis.ohio-state.edu and pollack@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/jung.selection_examples.ps.Z, 19960111 Universit at W urzburg Institut f ur Theoretische Physik Am Hubland, D{97074 W urzburg, Germany Selection of Examples for a Linear Classifier Georg Jung and Manfred Opper Ref.: WUE-ITP-95-022 e-mail : georgju@physik.uni-wuerzburg.de ftp : ftp.physik.uni-wuerzburg.de Selection of Examples for a Linear
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR03.ps.gz, 19960118 An Optimal Algorithm for Generalized Causal Message Ordering Ajay D. Kshemkalyani IBM Corporation Dept. C95A / Bldg. 664 P. O. Box 12195 Research Triangle Park NC 27709 Email: ajayk@vnet.ibm.com Phone: (919) 254-4370 Mukesh Singhal Dept of Computer and Information Science The Ohio State University 2015
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR04.ps.gz, 19960118 Tech. Report OSU-CISRC-1/96-TR04, Comp. & Info. Sci., Ohio State, 1996 1 Spatial Aggregation: language and applications Christopher Bailey-Kellogg Feng Zhao y Kenneth Yip z January 18, 1996
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr05-96-clus_mesh.ps.Z, 19960122 Designing Processor-cluster Based Systems: Interplay Between Cluster Organizations and Collective Communication Algorithms Debashis Basak and Dhabaleswar K. Panda Technical Report OSU-CISRC-01/96-TR05 1 Designing Processor-cluster Based Systems: Interplay Between Cluster Organizations and Collective
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR05.ps.gz, 19960122 Designing Processor-cluster Based Systems: Interplay Between Cluster Organizations and Collective Communication Algorithms 1 D. Basak and D. K. Panda Dept. of Computer and Information Science The Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR07.ps.gz, 19960129 Multimedia Database Systems: Challenges and Opportunities Yelena Yesha Dept. of Computer Science University of Maryland 5401 Wilkens Avenue Baltimore, MD Mukesh Singhal Department of Computer and Information Science The Ohio State University 2015 Neil Avenue Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR08.ps.gz, 19960201 Submitted to IEEE Transactions on Computer Graphics and Visualization Reconstruction Error Characterization and Control: A Sampling Theory Approach Raghu Machiraju and Roni Yagel Department of Computer and Information Science The Advanced Computing Center for the Arts and Design The Ohio State
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR10.ps.gz, 19960205 1 The Active-Ray Approach to Rendering on Distributed Memory Multiprocessors Asish Law and Roni Yagel Department of Computer and Information Science The Ohio State University 2036 Neil Avenue, Columbus, OH 43210-1277 USA {law, yagel}@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR09.ps.gz, 19960206 Submitted to VBC 96 Wavelet Based Feature Driven Identification and Enhancement of Medical Images Raghu Machiraju1,2, Ajeetkumar Gaddipati3 and Roni Yagel1,2 Department of Computer and Information Science1 The Advanced Computing Center for the Arts and Design2 Department of Biomedical Engineering3 The
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR11.ps.gz, 19960207 1 An Optimal Ray Traversal Scheme for Visualizing Colossal Medical Volumes Asish Law and Roni Yagel Department of Computer and Information Science The Ohio State University Columbus, Ohio
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR06.ps.gz, 19960212 The Intractability of Face Reachability in 3D Visit-Once Piecewise-Constant Derivative Systems John F. Kolen1 Feng Zhao2 Laboratory for Artificial Intelligence Research Department of Computer and Information Science The Ohio State University Columbus, OH 43210
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wallisgm.temporalobjrec2.ps.Z, 19960220 1 Using Spatio-Temporal Correlations to Learn Invariant Object Recognition Guy Wallis Max-Planck Institute f ur biologische Kybernetik, Spemannstrasse 38, 72076 T ubingen, Germany. Email: guy@mpik-tueb.mpg.de A competitive network is described which learns to classify objects on the basis of temporal as
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wallisgm.temporalobjrec1.ps.Z, 19960220 Optimal, Unsupervised Learning in Invariant Object Recognition Guy Wallis1 Max-Planck Institute f ur biologische Kybernetik, Spemannstrasse 38, 72076 T ubingen, Germany. Email: guy@mpik-tueb.mpg.de Roland Baddeley Dept. Experimental Psychology, University of Oxford, South Parks Road, Oxford OX1 3UD,
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/kershaw.nips8.ps.Z, 19960220 Context-Dependent Classes in a Hybrid Recurrent Network-HMM Speech Recognition System Dan Kershaw Tony Robinson Mike Hochberg Cambridge University Engineering Department, Trumpington Street, Cambridge CB2 1PZ, England. Tel: 1223 332800, Fax: 1223 332662. Email: djk, ajr @eng.cam.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wallisgm.ittrain.ps.Z, 19960220 A Model of Invariant Object Recognition in the Visual System Guy Wallis Edmund T. Rolls February 15, 1996 Oxford University, Department of Experimental Psychology, South Parks Road, Oxford OX1 3UD, England.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/korning.nnga.ps.Z, 19960220 -1- Training Neural Networks by means of Genetic Algorithms Working on Very Long Chromosomes Peter G. Korning Computer Science Department Aarhus University Ny Munkegade, Building 540 DK 8000 Aarhus C Denmark Email: aragorn@daimi.aau.dk -2- there s nothing like millions of years of really frustrating
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zecchina.committee.ps.Z, 19960220 Learning and Generalization Theories of Large Committee{Machines R emi Monasson and Riccardo Zecchinay Laboratoire de Physique Th eorique de l'ENS, 24 rue Lhomond, 75231 Paris cedex 05, France y INFN and Dip. di Fisica, Politecnico di Torino, C.so Duca degli Abruzzi 24, I-10129 Torino, Italy (28
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hofmann.cont_bayes.ps.Z, 19960220 In: "Advances in Neural Information Processing Systems 8," MIT Press, Cambridge MA, 1996. Discovering Structure in Continuous Variables Using Bayesian Networks Reimar Hofmann and Volker Tresp Siemens AG, Central Research Otto-Hahn-Ring 6 81730 M unchen, Germany
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR12.ps.gz, 19960227 Performance Study of Buffer Management Schemes under Multicasting Traffic in ATM Switching Nodes Khalid H. Sheta and Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 email: sheta@cis.ohio-state.edu, singhal@cis.ohio-state.edu Phone: 614-292-5839
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR13.ps.gz, 19960301 Multitolerance in Distributed Reset Sandeep S. Kulkarni Anish Arora Department of Computer and Information Science 1 The Ohio State University Columbus, Ohio 43210 USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR14.ps.gz, 19960304 Bandwidth-Optimal Complete Exchange on Wormhole-Routed 2D/3D Torus Networks: A Diagonal-Propagation Approach x Yu-Chee Tseng1, Ting-Hsien Lin2, Sandeep K. S. Gupta3, and Dhabaleswar K. Panda2
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr14-96-compl-exchange.ps.Z, 19960305 Bandwidth-Optimal Complete Exchange on Wormhole-Routed 2D/Torus Networks: A Diagonal-Propagation Approach Yu-Chee Tseng, Ting-Hsien Lin, Sandeep K. S. Gupta, and Dhabaleswar K. Panda Technical Report OSU-CISRC-3/96-TR14 IEEE Transactions on Parallel and Distributed Systems, under review. 1
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR17.ps.gz, 19960325 Stepwise Design of Tolerances in Barrier Computations Sandeep S. Kulkarni Anish Arora Department of Computer and Information Science 1 The Ohio State University Columbus, Ohio 43210 USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR16.ps.gz, 19960325 Finding Consistent Global Checkpoints in a Distributed Computation D. Manivannan Robert H. B. Netzery Mukesh Singhalz
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR19.ps.gz, 19960329 Universal Constructs in Distributed Computations Ajay D. Kshemkalyani IBM Corporation P. O. Box 12195 Research Triangle Park NC 27709 Mukesh Singhal Dept of Comp. & Info. Sci. The Ohio State University 2015 Neil Avenue Columbus, OH 43210 March 18, 1996
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR20.ps.gz, 19960401 A Foundation for Designing Deadlock-free Routing Algorithms in Wormhole Networks D. N. Jayasimha D. Manivannan Jeff A. May Department of Computer and Information Science The Ohio State University 395 Dreese Lab, 2015 Neil Ave. Columbus, OH 43210-1277 fjayasim, manivann, may-jg@cis.ohio-state.edu Loren
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/chesnokov.polynom_approx.ps.Z, 19960403 1 Fast Training Analog Approximator on the Basis of Legendre Polynomials Vyacheslav N. Chesnokov Institute of Radioengineering and Electronics of the Russian Academy of Sciences, Fryazino, Moscow Region, Russia 141120. E-mail: chesnokov@glas.apc.org
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/abdi.delta-gen.ps.Z, 19960403 Vol. 40, No.1, March 1996, pp. *{*. / Journal of Mathematical Psychology A Widrow-Hoff learning-rule for a generalization of the linear auto-associator Herv e Abdi y, Dominique Valentin , Betty Edelman , & Alice J. O'Toole The University of Texas at Dallas, and yUniversit e de Bourgogne a Dijon. A
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/neuneier.q-learning.ps.Z, 19960403 Optimal Asset Allocation using Adaptive Dynamic Programming Ralph Neuneier Siemens AG, Corporate Research and Development Otto-Hahn-Ring 6, D-81730 M unchen, Germany
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/waterhouse.const-hme-nips8.ps.Z, 19960403 Constructive Algorithms for Hierarchical Mixtures of Experts S.R.Waterhouse A.J.Robinson Cambridge University Engineering Department, Trumpington St., Cambridge, CB2 1PZ, England. Tel: 1223 332754, Fax: 1223 332662, Email: srw1001, ajr @eng.cam.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/chan.syntactic.ps.Z, 19960403 Efficient Connectionist Representations of Syntactic Parse Trees for Grammatical Inference HO, Kei Shiu Edward CHAN, Lai Wany Department of Computer Science and Engineering The Chinese University of Hong Kong Shatin, N.T., Hong Kong
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/waterhouse.bayes-me-nips8.ps.Z, 19960403 To appear in Neural Information Processing Systems 8, MIT Press Bayesian Methods for Mixtures of Experts Steve Waterhouse Cambridge University Engineering Department Cambridge CB2 1PZ England Tel: 1223 332754 srw1001@eng.cam.ac.uk David MacKay Cavendish Laboratory Madingley Rd. Cambridge CB3 0HE
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dingankar.tensor-products2.ps.Z, 19960403 c IEEE 1996. Invited paper at ISCAS, Atlanta, Georgia, May 13{15, 1996 1 TENSOR PRODUCT NEURAL NETWORKS AND APPROXIMATION OF DYNAMICAL SYSTEMS Ajit T. Dingankar1 Irwin W. Sandberg2 1 IBM Corporation Austin, TX 78758, U.S.A. ajit@austin.ibm.com 2 The University of Texas at Austin Austin, TX 78712, U.S.A.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR21.ps.gz, 19960404 Building Efficient Limited Directory-Based DSMs: A Multidestination Message Passing Based Approach1 Donglai Dai and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR22.ps.gz, 19960414 A Dynamic Approach to Location Management in Mobile Computing Systems Ravi Prakash Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210. E-mail: fprakash,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR23.ps.gz, 19960419 Analyzing Regression Test Selection Techniques1 Gregg Rothermel and Mary Jean Harrold Department of Computer and Information Science Ohio State University 395 Dreese Lab, 2015 Neil Avenue Columbus, OH 43210-1277 fgrother,harroldg@cis.ohio-state.edu April 12, 1996
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR24.ps.gz, 19960419 Reducing Cache Invalidation Overheads in Wormhole Routed DSMs Using Multidestination Message Passing1 Donglai Dai and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR27.ps.gz, 19960422 Classification and Local Error Estimation of Interpolation and Derivative Filters for Volume Rendering Torsten M ller1,3, Raghu Machiraju1,3, Klaus Mueller2, Roni Yagel1,2,3 1Department of Computer and Information Science 2Biomedical Engineering Center 3The Advanced Computing Center for the Arts and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR25.ps.gz, 19960423 A Safe, Efficient Regression Test Selection Technique1 Gregg Rothermel and Mary Jean Harrold Department of Computer and Information Science The Ohio State University 395 Dreese Lab, 2015 Neil Avenue Columbus, OH 43210-1277 fgrother,harroldg@cis.ohio-state.edu April 22, 1996
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR28.ps.gz, 19960426 Potential Networking Applications of Global Positioning Systems (GPS)1 Gopal Dommety, Raj Jain Department of Computer and Information Science The Ohio State University Columbus, OH 43210-1277 Contact: Jain@ACM.Org
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.third-generation.ps.Z, 19960503 Networks of Spiking Neurons: The Third Generation of Neural Network Models Wolfgang Maass Institute for Theoretical Computer Science Technische Universitaet Graz Klosterwiesgasse 32/2 A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at April 18, 1996
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/sollich.queries_comm_machine.ps.Z, 19960503 Learning from minimum entropy queries in a large committee machine Peter Sollich Department of Physics, University of Edinburgh, Kings Buildings, Mayfield Road, Edinburgh EH9 3JZ, U.K. In supervised learning, the redundancy contained in random examples can be avoided by learning from queries. Using
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/maass.sigmoidal-spiking.ps.Z, 19960503 An Efficient Implementation of Sigmoidal Neural Nets in Temporal Coding with Noisy Spiking Neurons Wolfgang Maass Institute for Theoretical Computer Science Technische Universitaet Graz Klosterwiesgasse 32/2 A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/zecchina.ksat.ps.Z, 19960503 The Entropy of the K{Satisfiability Problem R emi Monasson and Riccardo Zecchinay Laboratoire de Physique Th eorique de l'ENS, 24 rue Lhomond, 75231 Paris cedex 05, France y INFN and Dip. di Fisica, Politecnico di Torino, C.so Duca degli Abruzzi 24, I-10129 Torino, Italy The threshold behaviour of the
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR38.ps.gz, 19960504 Dependency Sequences and Hierarchical Clocks: Efficient Alternatives to Vector Clocks for Mobile Computing Systems Ravi Prakash Mukesh Singhal Department of Computer and Information Science The Ohio State University 2015 Neil Avenue Columbus, Ohio 43210.
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/qian.cd.ps.Z, 19960512 Binocular receptive field models, disparity tuning, and characteristic disparity Yu-Dong Zhu and Ning Qian Center for Neurobiology and Behavior Columbia University New York, NY 10032 Abbreviated title: Binocular receptive field models and disparity tuning Send all correspondence to: Dr. Ning Qian Center
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR29.ps.gz, 19960514 1 Hardware Assisted Volume Rendering of Unstructured Grids by Incremental Slicing Roni Yagel, David M. Reed, Asish Law, Po-Wen Shih, and Naeem Shareef Department of Computer and Information Science The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR31.ps.gz, 19960521 Covariance, Contravariance, and Synchronization Constraints Neelam Soundarajan Computer and Information Science The Ohio State University Columbus, OH 43210 USA e-mail: neelam@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dogaru.icnn95.ps.Z, 19960522 Chaotic Resonance Theory, a New Approach for Pattern Storage and Retrieval in Neural Networks1 Radu Dogaru, A.T. Murgan Politehnica University of Bucharest, Applied Electronics Department, Spl. Independentei Nr. 313, Sector 6, Bucharest, ROMANIA, Tel: +40-1-4105400/ ext. 140 E-Mail: radu_d@lmn.pub.ro ;
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/nakisahahn.cogsci96.ps.Z, 19960522 Where Defaults Don't Help: the Case of the German Plural System Ramin Charles Nakisa and Ulrike Hahn Department of Experimental Psychology, Oxford University South Parks Road Oxford, OX1 3UD framin,ulrikeg@psy.ox.ac.uk
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/dogaru.icnn96.ps.Z, 19960522 Searching for Robust Chaos in Discrete Time Neural Networks using Weight Space Exploration1 Radu Dogaru, A.T. Murgan, S. Ortmann, M. Glesner Applied Electronics Department, University Politehnica of Bucharest, Bd. Armata Poporului Nr.1, Sect.6, Bucharest, Romania, * Institute of Microelectronic
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR32.ps.gz, 19960529 Syntax-Directed Construction of Program Dependence Graphs 1 Mary Jean Harrold and Gregg Rothermel Department of Computer and Information Science The Ohio State University Columbus, OH 43210-1277 fharrold,grotherg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR33.ps.gz, 19960530 Quasi-Synchronous Checkpointing: Models, Characterization, and Classification D. Manivannan Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 (email: fmanivann,singhalg@cis.ohio-state.edu)
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/boyd/thesis.ps.gz, 19960604 Floor Control in Synchronous Groupware By John Alfred Boyd, Jr., Ph.D. The Ohio State University, 1996 Dr. Gary Perlman, Adviser Floor control in synchronous groupware is the problem of how, when, and why participants interact in a shared computing environment while working simultaneously on common
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR34.ps.gz, 19960606 Modeling Modular Software Structure for Human Understanding Stephen H. Edwards Dept. of Computer and Information Science The Ohio State University 2015 Neil Avenue Columbus, Ohio 43210{1277 E-Mail: edwards@cis.ohio-state.edu URL: http://www.cis.ohio-state.edu/ edwards
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-012.ps.gz, 19960613 ANATOMY-BASED SURFACE GENERATION FOR ARTICULATED MODELS OF HUMAN FIGURES By Coenraad Frederik Scheepers, Ph.D. The Ohio State University, 1996 Dr. Richard E. Parent, Adviser This research addresses the problem of creating realistic human figures for human figure animation applications. Anatomy-based
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-CBI.ps.gz, 19960613 APPENDIX C SYSTEM OVERVIEW C.1 Introduction The anatomy-based models described in this dissertation are implemented using a procedural modeling and animation language called Al . Al provides con- venient facilities for modeling and animating three-dimensional (3d) geometric ob- jects. In Al, all
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-5.ps.gz, 19960613 CHAPTER V MODELING MUSCLES AND TENDONS 5.1 Introduction The preceding chapter presents a model for the skeletal support of human figures in which individual bones and instances of different joint types are arranged into a hierarchical structure. Evaluation of this structure results in the creation of a
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-6.ps.gz, 19960613 CHAPTER VI MODELING SKIN AND FATTY TISSUE 6.1 Introduction The preceding chapter presents a number of anatomy-based models of muscles and tendons, and discusses their integration into a hierarchical definition of an articulated structure. The creation of muscles (and tendons) relative to the bones of an
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/torkkola.nnsp96.ps.Z, 19960613 IEEE workshop on Neural Networks for Signal Processing, Kyoto, Japan, Sept 4-6 1996 1 BLIND SEPARATION OF CONVOLVED SOURCES BASED ON INFORMATION MAXIMIZATION Kari Torkkola Motorola, Inc., Phoenix Corporate Research Laboratories 2100 E. Elliot Rd, MD EL508, Tempe AZ 85284, USA tel: (602)413-4129, fax:
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/almeida.icnn96.ps.Z, 19960613 Copyright (c) 1996 Institute of Electrical and Electronics Engineers. Reprinted, with permission, from proceedings of the IEEE International Conference on Neural Networks 1996 This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-7A.ps.gz, 19960613 CHAPTER VII CONCLUSION The two main difficulties in creating realistic human figure animation are related to faithfully representing the human body, and to controlling its motion effectively. This dissertation addresses the representation problem by developing an anatomybased human body model that
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-4a.ps.gz, 19960613 CHAPTER IV MODELING BONES AND JOINTS 4.1 Introduction The preceding chapter identifies and describes the anatomical structures that create and influence surface form: the skeleton, the articular system, the musculature, and the integument. The discussion focusses on all parts of the human body,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-B.ps.gz, 19960613 APPENDIX B ANATOMY OF THE UPPER LIMB B.1 Introduction The anatomy-based models described in this dissertation are utilized and tested in the context of modeling the right upper limb, an intricate articulated structure that proves to be an excellent testbed for model development . The principle
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/torkkola.icassp96.ps.Z, 19960613 Proceedings of the IEEE International Conference on Acoustics, Speech & Signal Processing, May 7-10 1996, Atlanta, GA, USA BLIND SEPARATION OF DELAYED SOURCES BASED ON INFORMATION MAXIMIZATION Kari Torkkola Motorola, Inc., Phoenix Corporate Research Laboratories, 2100 E. Elliot Rd, MD EL508, Tempe, AZ
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-3.ps.gz, 19960613 CHAPTER III ANATOMICAL STRUCTURES AND THEIR INFLUENCE ON SURFACE FORM 3.1 Introduction Artistic anatomy is the specialization in anatomy of most interest in this research. In artistic anatomy, structures that create and affect surface form are the primary focus . Artistic anatomy is more selective
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fry.neurmech.ps.Z, 19960613 Neural Mechanics Robert L. Fry The Johns Hopkins University/Applied Physics Laboratory Laurel, MD USA 20723-6099 robert_fry@jhuapl.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/dissertations/scheepers/CFS-4b.ps.gz, 19960613 4.4. A CASE STUDY: MODELING THE UPPER LIMB SKELETON 89 (define (make-hand-skeleton) ;; HIERARCHY (lambda (model "clenching-hand" (clench) (let ((direct (clench)) ;; alias (clench) (delay (expt (clench) 5))) ;; slow-down movement of thumb-1 (carpals) (metacarpals-2-5) ;; thumb hierarchy (separator
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR35.ps.gz, 19960620 Benefits of Processor Clustering in Designing Parallel Systems: When and How Debashis Basak and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Email: fbasak,pandag@cis.ohio-state.edu Contact Author: Dhabaleswar K. Panda
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr35-96-benefits_clustering.ps.Z, 19960621 Benefits of Processor Clustering in Designing Large Parallel Systems: When and How D. Basak and D. K. Panda Technical Report OSU-CISRC-6/96-TR35 Benefits of Processor Clustering in Designing Parallel Systems: When and How Debashis Basak and Dhabaleswar K. Panda Dept. of Computer and Information Science
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR36.ps.gz, 19960701 Failure Recovery based on Quasi-Synchronous Checkpointing in Mobile Computing Systems D. Manivannan and M. Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210. E-mail: fmanivann,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR37.ps.gz, 19960708 Multitolerance (Extended Abstract) Anish Arora Sandeep S. Kulkarni Department of Computer and Information Science 1 The Ohio State University Columbus, Ohio 43210 USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR39.ps.gz, 19960719 An Efficient Protocol for Call Setup and Path Migration in IEEE 802.6 Based Personal Communication Networks Xuefeng Dong and Ten-Hwang Lai Department of Computer and Information Science The Ohio State University lai@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/mathia.invnn.ps.Z, 19960728 World Congress on Neural Networks 1996, San Diego, California. 7 then the point is not the minimum any longer, but is still in the positive definite neighborhood of the new minimum. It can therefore be used as the new initial condition. If this process is repeated, the subsequent optimization processes
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/friedrich.ipmu96.ps.Z, 19960728 An Evolutionary Method to Find Good Building-Blocks for Architectures of Artificial Neural Networks Christoph M. Friedrich University of Witten/Herdecke Inst. for Technology Development and Systems Analysis Alfred-Herrhausen Str. 44 58455 Witten, Germany chris@uni-wh.de Claudio Moraga University of
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/parga.dynrf.ps.Z, 19960728 Dynamics of receptive fields in the visual system: plasticity of intra-cortical connections G. Mato and N. Parga Departamento de F sica Te orica C-XI Ciudad Universitaria de Cantoblanco Universidad Aut onoma de Madrid 28049 Madrid Spain
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/parga.bss.ps.Z, 19960728 Redundancy Reduction and Independent Component Analysis: Conditions on Cumulants and Adaptive Approaches Jean-Pierre Nadal Laboratoire de Physique Statistique de l'E.N.S.* Ecole Normale Sup erieure 24, rue Lhomond, F-75231 Paris Cedex 05, France Nestor Parga Departamento de F sica Te orica Universidad
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/parga.timdepbss.ps.Z, 19960728 Blind Source Separation with Time Dependent Mixtures Nestor Parga Departamento de F sica Te orica Universidad Aut onoma de Madrid Cantoblanco, 28049 Madrid, Spain Jean-Pierre Nadal Laboratoire de Physique Statistique de l'ENS* Ecole Normale Sup erieure 24, rue Lhomond, 75231 Paris Cedex 05, France
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR40.ps.gz, 19960731 Multicast on Irregular Switch-based Networks with Wormhole Routing 1 Ram Kesavan, Kiran Bondalapati, and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr21-96-limited-rb.ps.Z, 19960802 Building Efficient Limited Directory-Based DSMs: A Multidestination Message Passing Based Donglai Dai and Dhabaleswar K. Panda Technical Report OSU-CISRC-4/96-TR21 1 Building Efficient Limited Directory-Based DSMs: A Multidestination Message Passing Based Approach1 Donglai Dai and Dhabaleswar K. Panda
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr41-96-consumption.ps.Z, 19960802 Alleviating Consumption Channel Bottleneck in Wormhole-Routed k-ary n-cube Systems Debashis Basak and Dhabaleswar K. Panda Technical Report OSU-CISRC-8/96-TR41 Manuscript is under review for IEEE Transactions of Parallel and Distributed Systems. 1 Alleviating Consumption Channel Bottleneck in
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR41.ps.gz, 19960802 Alleviating Consumption Channel Bottleneck in Wormhole-Routed k-ary n-cube Systems 1 Debashis Basak and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 Email: fbasak,pandag@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr40-96-mcast_irreg.ps.gz, 19960802 Multicast on Irregular Switch-based Networks with Wormhole Routing Ram Kesavan, Kiran Bondalapati, and Dhabaleswar K. Panda Technical Report OSU-CISRC-7/96-TR40 Manuscript has been submitted to International Symposium on High Performance Computer Architecture (HPCA '97). 1 Multicast on Irregular
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR42.ps.gz, 19960815 RMSP: A Reliable Multicast Session Protocol for Collaborative Continuous-Feed Applications Walid Mostafa Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 email: (mostafa,singhal)@cis.ohio-state.edu Phone: 614-292-5839 Fax: 614-292-2991
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR43.ps.gz, 19960823 An Efficient Coterie-Based Mutual Exclusion Scheme With Fault-tolerance Capability Guohong Cao, Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43201 E-mail: fgcao, singhalg@cis.ohio-state.edu Yi Deng, Naphtali Rishe, and Wei Sun School of Computer
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR26.ps.gz, 19960827 Multiple Multicast with Minimized Node Contention on Wormhole k-ary n-cube Networks Ram Kesavan and Dhabaleswar K. Panda Technical Report OSU-CISRC-4/96-TR26 Manuscript has been submitted to IEEE Transactions on Parallel and Distributed Systems. 1 Multiple Multicast with Minimized Node Contention on
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR44.ps.gz, 19960827 Classes as Assertions Neelam Soundarajan Computer and Information Science The Ohio State University Columbus, OH 43210 e-mail: neelam@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/korucheva.binary.ps.Z, 19960902 Information Processing by a Noisy Binary Channel Elka Korutcheva Departamento de F isica Te orica Universidad Aut onoma de Madrid Canto Blanco, 28049 Madrid, Spain Nestor Parga Departamento de F isica Te orica Universidad Aut onoma de Madrid Canto Blanco, 28049 Madrid, Spain Jean-Pierre Nadal
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr15-96-mport_enc.ps.gz, 19960909 Efficient Broadcast and Multicast on Multistage Interconnection Networks using Multiport Encoding RAJEEV SIVARAM, DHABALESWAR K. PANDA, AND CRAIG B. STUNKEL Technical Report OSU-CISRC-3/96-TR15 A preliminary version of this manuscript has been accepted for presentation in the Eighth IEEE Symposium on
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR15.ps.gz, 19960911 Efficient Broadcast and Multicast on Multistage Interconnection Networks using Multiport Encoding Rajeev Sivaram and Dhabaleswar K. Panda Craig B. Stunkel Dept. of Computer and Information Science I.B.M. T. J. Watson Research Center The Ohio State University P. O. Box 218 Columbus, OH 43210-1277
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cohen.prior-tts-figs.ps.Z, 19960924 Hidden 100 Output 40 Input Dim 220 Phoneme SOM Diphone SOM Output Speech Text Input Multiple MLP Networks Previously trained Corrector Network Figure 1. SOMtalk architcture Hidden 40 - 220 Output 40AA units 25 Input Dim 220 1 1 Figure 3. Correction performed by encode network (on-line training) Output
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR45.ps.gz, 19960925 Reliable Hardware Barrier Synchronization Schemes Rajeev Sivaram Craig B. Stunkely Dhabaleswar K. Panda Dept. of Computer and Information Science I.B.M. T. J. Watson Research Centery The Ohio State University P. O. Box 218 Columbus, OH 43210 Yorktown Heights, NY 10598 Email:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_abr22.ps.gz, 19960928 Raj Jain The Ohio State University 1 96-0517R1 Buffer Requirements 96-0517R1 Buffer Requirements 96-0517R1 Buffer Requirements for TCP over ABR for TCP over ABR for TCP over ABR Raj Jain, Shiv Kalyanaraman, Rohit Goyal, Sonia Fahmy The Ohio State University Saragur M. Srinidhi Sterling Software and NASA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR46.ps.gz, 19960928 Efficient Scatter Communication in Wormhole k-ary n-cubes with Multidestination Message Passing 1 Mohammad Banikazemi and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR53.ps.gz, 19960928 ATM Forum Document Number: ATM Forum/96-1267 Title: ABR Switch Algorithm Testing: A Case Study with ERICA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR51.ps.gz, 19960928 ATM Forum Document Number: ATM Forum/96-1172 Title: ERICA Switch Algorithm: A Complete Description
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr46-96-scatter.ps.Z, 19960928 Efficient Scatter Communication in Wormhole k-ary n-cubes with Multidestination Message Passing Mohammad Banikazemi and Dhabaleswar K. Panda Technical Report OSU-CISRC-9/96-TR46 1 Efficient Scatter Communication in Wormhole k-ary n-cubes with Multidestination Message Passing 1 Mohammad Banikazemi and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR54.ps.gz, 19960928 ATM Forum Document Number: ATM Forum/96-1270 Title: Tutorial Paper on ABR Source Behavior
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_ubr22.ps.gz, 19960928 Raj Jain The Ohio State University 1 96-0518R1 TCP over UBR 96-0518R1 TCP over UBR 96-0518R1 TCP over UBR and Its Buffer Requirements and Its Buffer Requirements and Its Buffer Requirements Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Rohit Goyal, Shiv Kalyanaraman,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR52.ps.gz, 19960928 Rohit Goyal, Performance of TCP/IP over UBR+ 1 ATM Forum Document Number: ATM_Forum/96-1269 Title: Performance of TCP over UBR+
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_erc22.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-1346R1 ERICA+: Extensions to the ERICA Switch Algorithm Contact: Jain@cis.ohio-state.edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Shiv Kalyanaraman, Rohit Goyal, Sonia Fahmy, Fang Lu The Ohio State University Dept of Computer and Information Science
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_brst2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-1345R1 Bursty ABR Sources Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Shiv Kalyanaraman, Sonia Fahmy, Fang Lu The Ohio State University Department of CIS Columbus, OH 43210 Raj Jain The Ohio State University 2 q Bursty traffic
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_cif2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-1344R1 New Source Rules and Satellite Links Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~jain/ Raj Jain, Shiv Kalyanaraman, Fang Lu, Sonia Fahmy The Ohio State University Saragur M. Srinidhi Sterling Software and NASA Lewis Research Center Raj
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_rl62.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-1661R1 TBE vs Queue Sizes Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Sonia Fahmy, Shiv Kalyanaraman, Rohit Goyal, Fang Lu The Ohio State University Saragur M. Srinidhi Sterling Software and NASA Lewis Research Center Raj Jain
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_trans.ps.gz, 19960929 Raj Jain The Ohio State University 94-1173 Transient Performance of EPRCA and EPRCA++ Raj Jain, Shiv Kalyanaraman, Ram Viswanathan Department of CIS The Ohio State University Columbus, OH 43210-1277 Jain@ACM.Org Raj Jain The Ohio State University q Why worry about transient performance q Transient
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_rl6b2.ps.gz, 19960929 Raj Jain The Ohio State University 1 96-0177R1 96-0177R1 96-0177R1 TCP/IP over ABR TCP/IP over ABR TCP/IP over ABR Was: TBE and TCP/IP Traffic] Was: TBE and TCP/IP Traffic] Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Shiv Kalyanaraman,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_rl5b2.ps.gz, 19960929 Raj Jain The Ohio State University 1 96-0178R1 Comments on Use-it or Lose-it (Annex F of TM4.0) Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Shiv Kalyanaraman, Rohit Goyal, Sonia Fahmy, Fang Lu The Ohio State University Saragur M. Srinidhi Sterling Software and NASA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_trm2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-0973R1 Out-of-Rate RM Cell Issues and Effect of Trm, TOF, and TCR on Low Rate Sources Contact: Jain@ACM.Org http://www.cis.ohio-state.edu/~jain/ Raj Jain, Shiv Kalyanaraman, Sonia Fahmy, Fang Lu Department of Computer and Information Sciences The Ohio State
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_xrm2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-0972R1 Parameter Values for Satellite Links Contact: Jain@ACM.Org http://www.cis.ohio-state.edu/~jain/ Raj Jain, Shiv Kalyanaraman, Sonia Fahmy, Fang Lu The Ohio State University Saragur M. Srinidhi Sterling Software and NASA Lewis Research Center Raj Jain The
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_swsi2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-0179 Simulation Results for The Sample Switch Algorithm Raj Jain, Shiv Kalyanaraman, Ram Viswanathan, Rohit Goyal Department of CIS The Ohio State University Columbus, OH 43210-1277 Jain@ACM.Org Raj Jain The Ohio State University 2 q Why worry about transient
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_osu2.ps.gz, 19960929 Raj Jain The Ohio State University 94-088394-0883 The OSU SchemeThe OSU Scheme Raj Jain, Shiv Kalyanraman, Ram Viswanathan Department of Computer and Information Sci. The Ohio State University Columbus, OH 43210 Jain@ACM.Org Raj Jain The Ohio State University q Features qScheme q Simulation results
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_stvc2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-1343R1 Straw-Vote Comments on TM4.0 R8 Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Shiv Kalyanaraman, Sonia Fahmy, Fang Lu The Ohio State University Saragur M. Srinidhi Sterling Software and NASA Lewis Research Center Raj Jain
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_swco2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-0178 A Sample Switch Algorithm Raj Jain, Shiv Kalyanaraman, Ram Viswanathan, Rohit Goyal Department of CIS The Ohio State University Columbus, OH 43210-1277 Jain@ACM.Org Raj Jain The Ohio State University 2 qSwitch Algorithm qPseudocode q Simulation Results
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_becn.ps.gz, 19960929 Raj Jain The Ohio State University AF-TM 94-0987 Ordered BECN Raj Jain, Shiv Kalyanaraman, Ram Viswanathan Department of CIS The Ohio State University Columbus, OH 43210 Jain@ACM.Org Raj Jain The Ohio State University qWhy BECN s cause confusion q How to Fix it Overview Raj Jain The Ohio State
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_iss22.ps.gz, 19960929 Raj Jain The Ohio State University q Anything that hurts the transient performance should be optional. Key Issue Raj Jain The Ohio State University Summary q Minimize the impact of rare abnormal conditions on the normal path q Unnecessary decrease every time hurts transient performance
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr45-96-rel-barrier.ps.Z, 19960929 Reliable Hardware Barrier Synchronization Schemes Rajeev Sivaram, Craig B. Stunkel and Dhabaleswar K. Panda Technical Report OSU-CISRC-9/96-TR45 Reliable Hardware Barrier Synchronization Schemes Rajeev Sivaram Craig B. Stunkely Dhabaleswar K. Panda Dept. of Computer and Information Science I.B.M. T. J.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_osuc2.ps.gz, 19960929 Raj Jain The Ohio State University AF-TM 94-0988 and 94-0989 Simulation Results: The EPRCA+ Scheme Raj Jain, Shiv Kalyanaraman, Ram Viswanathan Department of CIS The Ohio State University Columbus, OH 43210-1277 Jain@ACM.Org Raj Jain The Ohio State University Steps to Future BECN EPRCA EPRCA+ Precise
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_9409-mistakes2.ps.gz, 19960929 Raj Jain The Ohio State University 94-088294-0882 Rate-Based Schemes:Rate-Based Schemes: Mistakes to AvoidMistakes to Avoid Raj Jain, Shiv Kalyanraman, Ram Viswanathan Department of Computer and Information Sci. The Ohio State University Columbus, OH 43210 Jain@ACM.Org Raj Jain The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_rl52.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-1660R1 A Fix for Source End System Rule 5 Contact: Jain@CIS.Ohio-State.Edu http://www.cis.ohio-state.edu/~Jain/ Raj Jain, Shiv Kalyanaraman, Rohit Goyal, Sonia Fahmy, Fang Lu The Ohio State University Saragur M. Srinidhi Sterling Software and NASA Lewis Research
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR55-DIR/af_vbr2.ps.gz, 19960929 Raj Jain The Ohio State University 1 95-0467 Simulation Results for VBR+ABR Traffic Raj Jain, Shiv Kalyanaraman, Rohit Goyal Department of CIS The Ohio State University Columbus, OH 43210-1277 Jain@ACM.Org http://www.cis.ohio-state.edu/~jain/ Raj Jain The Ohio State University 2 q Effect of VBR qVBR
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR49.ps.gz, 19961001 1 Range Image Segmentation Using a LEGION Network Xiuwen Liu and DeLiang Wang Department of Computer and Information Science Center for Cognitive Science The Ohio State University Columbus, Ohio 43210, USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR50.ps.gz, 19961001 Shiv Kalyanaraman, Performance of TCP over ABR on ATM backbone and with various VBR traffic patterns 1 Performance of TCP over ABR on ATM backbone and with various VBR traffic patterns Shiv Kalyanaraman, Raj Jain, Sonia Fahmy, Rohit Goyal and Jianping Jiang The Ohio State University Department of CIS
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR47-DIR/figs.ps.gz, 19961008 -0.3 -0.2 -0.1 0.1 0.2 0.3 1 2 3 4 5 t x Fig. 1 Fig. 2 Fig. 3 -5 5 10 15 20 -2 -1 1 2 x-nullcline LB y-nullcline RK RB LK x y -5 5 10 15 20 -2 -1 1 2 URK ULK
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR56.ps.gz, 19961014 Distributed Dynamic Carrier Allocation in Mobile Cellular Networks: Search vs. Update Xuefeng Dong and Ten H. Lai Department of Computer and Information Science The Ohio State University fdong, laig@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR47-DIR/TR47.ps.gz, 19961016 1 Relaxation Oscillators with Time Delay Coupling Shannon R. Campbell and DeLiang Wang Department of Physics Corresponding author: Department of Computer and Information Science and Center for Cognitive Science The Ohio State University, Columbus, Ohio 43210, U.S.A. (614) 292-6827 FAX (614) 292-2911
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/der.coherence.ps.Z, 19961021 Local Online Learning of Coherent Information Ralf Dery and Darragh Smythyxz Addresses y Universit at Leipzig, Institut f ur Informatik, Postfach 920, Leipzig 04009, Germany. x Psychology Department, Stirling University, Stirling FK9 4LA, UK. z University Laboratory of Physiology, Parks Road, Oxford OX1
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/malthouse.nlpca.ps.Z, 19961021 Some Theoretical Results on Nonlinear Principal Components Analysis Edward C. Malthouse September 19, 1996
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/cohen.prior-tts.ps.Z, 19961021 Embedding prior phonetic knowledge in a text-to-speech system using data driven methods. Technical Report Andrew D. Cohen, Department of Cybernetics, University of Reading. October 17, 1996
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/khan.thesis.ps.Z, 19961021 Feedforward Neural Networks with Constrained Weights Altaf Hamid Khan A thesis submitted in satisfaction of the requirements for the degree of Doctor of Philosophy University of Warwick Department of Engineering August 1996 c Altaf Hamid Khan, 1996. All rights reserved. Permission is granted in respect
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR48.ps.gz, 19961024 Dynamic Carrier Allocation Strategies for Mobile Cellular Networks Xuefeng Dong and Ten H. Lai Department of Computer and Information Science The Ohio State University fdong, laig@cis.ohio-state.edu October 23, 1996
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR58.ps.gz, 19961108 Analysis of Hierarchical Reliable Multicast Transport Protocols for Dissemination and Collaborative Communications Walid Mostafa Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 email: (mostafa,singhal)@cis.ohio-state.edu Phone: 614-292-5839 Fax:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR59.ps.gz, 19961112 Implementing Multidestination Worms in Switch Based Parallel Systems: Architectural Alternatives and their Impact Craig B. Stunkely Rajeev Sivaram Dhabaleswar K. Panda yI.B.M. T. J. Watson Research Center Dept. of Computer and Information Science P. O. Box 218 The Ohio State University Yorktown Heights,
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr59-96-mdest-arch-alt.ps.Z, 19961112 Implementing Multidestination Worms in Switch Based Parallel Systems: Architectural Alternatives and their Impact Craig B. Stunkel, Rajeev Sivaram and Dhabaleswar K. Panda Technical Report OSU-CISRC-11/96-TR59 Implementing Multidestination Worms in Switch Based Parallel Systems: Architectural
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR60.ps.gz, 19961120 A Coherent Family of Analyzable Graphical Representations for Object-Oriented Software Mary Jean Harrold and Gregg Rothermel Department of Computer and Information Science Ohio State University 395 Dreese Lab, Columbus OH, 43210 fharrold,grotherg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr61-96-multidest-dirB.ps.Z, 19961122 Efficient Schemes for Limited Directory-Based DSMs Using Multidestination Message Passing Donglai Dai and Dhabaleswar K. Panda Technical Report OSU-CISRC-11/96-TR61 1 Efficient Schemes for Limited Directory-based DSMs Using Multidestination Message Passing 1 Donglai Dai and Dhabaleswar K. Panda Dept. of
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR61.ps.gz, 19961125 Efficient Schemes for Limited Directory-based DSMs Using Multidestination Message Passing 1 Donglai Dai and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: fdai,pandag@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR62.ps.gz, 19961127 Logical Firewalls: A Mechanism for Security in Future Networking EnvironmentsNovember 26, 1996 25 Pfleeger, C. P., Security in Computing, 2nd ed., Prentice Hall PTR, Upper Saddle River, NJ, 1997 Cheswick, W. R., and S. M. Bellovin, Firewalls and Internet Security, Addison Wesley, Reading, MA,
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR63.ps.gz, 19961202 Inheriting and Modifying Behavior Neelam Soundarajan and Stephen Fridella Computer and Information Science The Ohio State University Columbus, OH 43210 e-mail: fneelam,fridellag@cis.ohio-state.edu November 27, 1996
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR65.ps.gz, 19961212 An Ef cient Priority-Based Dynamic Channel Allocation Strategy for Mobile Cellular Networks Xuefeng Dong and Ten H. Lai Department of Computer and Information Science The Ohio State University fdong, laig@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/Thesis/boue.thesis.ps.Z, 19961213 FeasPar - A Feature Structure Parser Learning to Parse Spontaneous Speech Zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften der Fakult at f ur Informatik der Universit at Karlsruhe (Technische Hochschule) vorgelegte Dissertation von Finn Dag Buo aus Stockholm, Schweden Tag
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/karaali.synthesis_wcnn96.ps.Z, 19961213 Speech Synthesis with Neural Networks Orhan Karaali, Gerald Corrigan, and Ira Gerson Motorola, Inc., 1301 E. Algonquin Road, Schaumburg, IL 60196 karaali@mot.com, corrigan@mot.com, gerson@mot.com
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR64.ps.gz, 19961216 A Comparison of Bandwidth Smoothing Techniques for the Transmission of Prerecorded Compressed Video Wu-chi Feng Jennifer Rexford Dept. of Comp. and Info. Sci. Networking and Distributed Systems Lab The Ohio State University AT&T Labs Research Columbus, OH 43210 Murray Hill, NJ 07974
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR66.ps.gz, 19961220 1 Time Constrained Bandwidth Smoothing for Interactive Video-On-Demand Systems Wu-chi Feng Department of Computer and Information Science The Ohio State University Columbus, OH 43210 wuchi@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR57.ps.gz, 19961226 A Distributed Fault-Detection and Recovery Protocol for Reliable Multicast Collaborative Communications Walid Mostafa Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 email: (mostafa,singhal)@cis.ohio-state.edu Phone: 614-292-5839 Fax:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR30.ps.gz, 19961226 Flexible Object Reconstruction from Temporal Image Series Jeremy Loomis1 Zhaohua Ding 2 Xiuwen Liu1 Kikuo Fujimura1 Hideo Ishikawa3 The Ohio State University
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR67-DIR/wangfig.ps.gz, 19970106 A Sun Tree Mountain Fast Inhibitor Slow Inhibitor Time B Sun Tree Mountain Fast Inhibitor Slow Inhibitor Time
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR67-DIR/wang.ps.gz, 19970106 1 Technical Report: OSU-CISRC-12/96 - TR67, 1996 Object Selection Based on Oscillatory Correlation DeLiang Wang Department of Computer and Information Science and Center for Cognitive Science The Ohio State University, Columbus, Ohio 43210, USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR01.ps.gz, 19970115 Tech Report OSU-CISRC-1/97-TR01, Comp. & Info. Sci., Ohio State U., 1997 1 Spatial Aggregation: Modeling and controlling physical fields Christopher Bailey-Kellogg Feng Zhao Department of Computer and Information Science The Ohio State University 2015 Neil Avenue Columbus, OH 43210 U.S.A.
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR02.ps.gz, 19970122 A Survey of the Use-It-Or-Lose-It Policies for the ABR Service in ATM Networks Shiv Kalyanaraman, Raj Jain, Rohit Goyal, Sonia Fahmy Department of Computer and Information Science The Ohio State University 2015 Neil Ave., Columbus, OH 43210-1277 E-mail: fshivkuma, jain, goyal, fahmyg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR03.ps.gz, 19970122 On the Speci cation, Inheritance, and Veri cation of Synchronization Constraints Neelam Soundarajan Computer and Information Science The Ohio State University Columbus, OH 43210 USA e-mail: neelam@cis.ohio-state.edu Key phrases: Speci cation and veri cation; Synchronization constraints; Inheritance
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR04.ps.gz, 19970127 Re ning Interactions in a Distributed System (Extended Abstract) Neelam Soundarajan Computer and Information Science The Ohio State University Columbus, OH 43210 USA e-mail: neelam@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR05.ps.gz, 19970127 Online Smoothing for Delayed Transmission of Live Video Jennifer Rexford Networking and Distributed Systems AT&T Labs Research; Murray Hill, NJ http://www.research.att.com/ jrex Wu-chi Feng Computer and Information Sciences Ohio State University; Columbus, OH http://www.cis.ohio-state.edu/ wuchi 1
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR06.ps.gz, 19970130 Efficient Multicast in IP/ATM Networks Walid Mostafa Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 email: (mostafa,singhal)@cis.ohio-state.edu Phone: 614-292-5839 Fax: 614-292-2991
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR07.ps.gz, 19970131 A Medium Access Control Protocol for Voice and Data Integration in Receiver-Oriented DS-CDMA PCNs Yibin Yang Junfeng He Ming T. Liu Department of Computer and Information Science The Ohio State University Columbus, Ohio 43210-1277 E-mail: fyyang, he, liug@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR08.ps.gz, 19970203 13 Levoy, M., A Hybrid Ray Tracer for Rendering Polygon and Volume Data , IEEE Comput- er Graphics & Applications, 10, 3 (March 1990), 33-40. Newman, W. M. and Sproull, R. F., Principles of Interactive Computer Graphics, (2nd ed.) McGraw-Hill, New York, 1979. Pavlidis, T., Algorithms for
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr26-96-multiple-multicast.ps.Z, 19970207 Multiple Multicast with Minimized Node Contention on Wormhole k-ary n-cube Networks Ram Kesavan and Dhabaleswar K. Panda Technical Report OSU-CISRC-4/96-TR26 A preliminary version of this paper has been presented in International Conference on Parallel Processing, Aug. 1996. Manuscript is under review
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr10-97-packet-mcast.ps.Z, 19970209 Optimal Multicast with Packetization and Network Interface Support Ram Kesavan and Dhabaleswar K. Panda Technical Report OSU-CISRC-2/97-TR10 1 Optimal Multicast with Packetization and Network Interface Support 1 Ram Kesavan and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR10.ps.gz, 19970210 Optimal Multicast with Packetization and Network Interface Support 1 Ram Kesavan and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: fkesavan,pandag@cis.ohio-state.edu Contact Author:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR11.ps.gz, 19970211 Can Scatter Communication Benefit from Multidestination Message Passing 1 Mohammad Banikazemi and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: fbanikaze,pandag@cis.ohio-state.edu Contact
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr11-97-scatter.ps.Z, 19970211 Can Scatter Communication Benefit from Multidestination Message Passing 1 Mohammad Banikazemi and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: fbanikaze,pandag@cis.ohio-state.edu Contact
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/hansel.if.ps.Z, 19970213 On numerical simulations of integrate-and-fire neural networks D. Hansel (1), G. Mato (2), C. Meunier (1) and L. Neltner (1) (1) Centre de Physique Th eorique UPR014 CNRS Ecole Polytechnique 91128 Palaiseau Cedex, France, (2) Centro At omico Bariloche Comisi on Nacional de Energ a Atomica, 8400 S. C. de
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/wermter.screen2.ps.Z, 19970213 Journal of Artificial Intelligence Research 6 (1997) 35-85 Submitted 7/96; published 1/97 SCREEN: Learning a Flat Syntactic and Semantic Spoken Language Analysis Using Artificial Neural Networks Stefan Wermter wermter@informatik.uni-hamburg.de Volker Weber weber@informatik.uni-hamburg.de Department of
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR12.ps.gz, 19970217 Re ning Interactions in a Distributed System (Extended Abstract) Neelam Soundarajan Computer and Information Science The Ohio State University Columbus, OH 43210 USA e-mail: neelam@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR13.ps.gz, 19970217 Interaction Re nement in Object-Oriented Systems (Extended Abstract) Neelam Soundarajan Computer and Information Science The Ohio State University 2015 Neil Avenue Mall Columbus, OH 43210 USA e-mail: neelam@cis.ohio-state.edu Tel: (614) 292 1444. FAX: (614) 292 2911
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR14.ps.gz, 19970220 How Much Does Network Contention Affect Distributed Shared Memory Performance Donglai Dai and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: fdai,pandag@cis.ohio-state.edu Contact Author:
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr14-97-cont-dsm.ps.Z, 19970221 How Much Does Network Contention Affect Distributed Shared Memory Performance Donglai Dai and Dhabaleswar K. Panda Technical Report OSU-CISRC-2/97-TR14 1 How Much Does Network Contention Affect Distributed Shared Memory Performance Donglai Dai and Dhabaleswar K. Panda Dept. of Computer and Information
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr24-96-red-inval.ps.Z, 19970226 Reducing Cache Invalidation Overheads in Wormhole Routed DSMs Using Multidestination Message Passing Donglai Dai and Dhabaleswar K. Panda Technical Report OSU-CISRC-4/96-TR21 1 Reducing Cache Invalidation Overheads in Wormhole Routed DSMs Using Multidestination Message Passing1 Donglai Dai and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR16.ps.gz, 19970226 Constructing Pairwise Disjoint Paths with Few Links Himanshu Gupta Rephael Wengery February 26, 1997
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR17.ps.gz, 19970304 Aristotle: A System for Research on and Development of Program-Analysis-Based Tools Mary Jean Harrold Department of Computer and Information Science, The Ohio State University. and Gregg Rothermel Department of Computer Science, Oregon State University. SUMMARY Aristotle provides program analysis
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1996/TR02.ps.gz, 19970310 The OSU Scheme for Congestion Avoidance in ATM Networks Using Explicit Rate Indication1 OSU-CIS Technical Report Number: OSU-CISRC-1/96-TR02 Raj Jain, Shiv Kalyanaraman and Ram Viswanathan Department of Computer and Information Science The Ohio State University Columbus, OH 43210-1277 Email:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR18.ps.gz, 19970312 Performance Evaluation of Smoothing Algorithms for Transmitting Prerecorded Variable-Bit-Rate Video Wu-chi Feng Computer and Information Sciences Ohio State University Columbus, OH 43210 wuchi@cis.ohio-state.edu Jennifer Rexford Networking and Distributed Systems AT&T Labs Research Murray Hill, NJ 07974
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR19.ps.gz, 19970326 How Can We Design Better Networks for DSM Systems Donglai Dai and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail: fdai,pandag@cis.ohio-state.edu Contact Author: Dhabaleswar K. Panda
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr19-97-dsm-net-guides.ps.Z, 19970326 How Can We Design Better Networks for DSM Systems Donglai Dai and Dhabaleswar K. Panda Technical Report OSU-CISRC-3/97-TR19 March 1997 1 How Can We Design Better Networks for DSM Systems Donglai Dai and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus,
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr20-97-tree_mdest_irreg.ps.Z, 19970326 Multicasting in Irregular Networks with Cut-Through Switches using Tree-Based Multidestination Worms Rajeev Sivaram, Dhabaleswar K. Panda, and Craig B. Stunkel Technical Report OSU-CISRC-3/97-TR20 Multicasting in Irregular Networks with Cut-Through Switches using Tree-Based Multidestination Worms Rajeev
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR20.ps.gz, 19970326 Multicasting in Irregular Networks with Cut-Through Switches using Tree-Based Multidestination Worms Rajeev Sivaramy Dhabaleswar K. Panday Craig B. Stunkelz yDept. of Computer and Information Science zIBM T. J. Watson Research Center The Ohio State University, Columbus, OH 43210 P. O. Box 218, Yorktown
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR21.ps.gz, 19970401 Multicasting on Switch-based Irregular Networks using Multi-drop Path-based Multidestination Worms 1 Ram Kesavan and Dhabaleswar K. Panda Dept. of Computer and Information Science The Ohio State University, Columbus, OH 43210-1277 Tel: (614)-292-5199, Fax: (614)-292-2911 E-mail:
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr21-97-multidrop_irreg.ps.Z, 19970402 Multicasting on Switch-based Irregular Networks using Multi-drop Path-based Multidestination Worms Ram Kesavan and Dhabaleswar K. Panda Technical Report OSU-CISRC-4/97-TR21 1 Multicasting on Switch-based Irregular Networks using Multi-drop Path-based Multidestination Worms 1 Ram Kesavan and Dhabaleswar
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR22.ps.gz, 19970410 Stepwise Design of Tolerances in Barrier Computations Sandeep S. Kulkarni Anish Arora Department of Computer and Information Science 1 The Ohio State University Columbus, Ohio 43210 USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR23.ps.gz, 19970414 An Introduction To RESOLVE/Ada95 Technical Report OSU-CISRC-4/97-TR23 11 April 1997 David S. Gibson The Ohio State University Department of Computer and Information Science Reusable Software Research Group http://www.cis.ohio-state.edu/hypertext/rsrg 2 AN INTRODUCTION TO RESOLVE/ADA95 Copyright 1997 by
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR25.ps.gz, 19970417 Scheduling Fork-Join Computations on Distributed-Memory Multiprocessor Systems Khalid H. Sheta, Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 email: sheta@cis.ohio-state.edu, singhal@cis.ohio-state.edu Phone: 614-292-5839 Fax: 614-292-2991 and
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR26-DIR/image1.ps.gz, 19970421 a b Figure 5 Figure 6 ba ba c d e f Figure 7 Figure 8 ba c d Figure 9 b c a
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR26-DIR/image2.ps.gz, 19970421 Figure 10 a b dc Figure 11 a b f Figure 11 e g h Figure 12 a b c d Figure 13 b a c d
	ftp://ftp.cis.ohio-state.edu/pub/communication/techreports/tr54-95-brcp.ps.Z, 19970504 Multidestination Message Passing in Wormhole k-ary n-cube Networks with Base Routing Conformed Paths Dhabaleswar K. Panda, Sanjay Singal, and Ram Kesavan Technical Report OSU-CISRC-12/95-TR54 1 Multidestination Message Passing in Wormhole k-ary n-cube Networks with Base Routing Conformed Paths1
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR24.ps.gz, 19970505 Technical Report OSU-CISRC-4/97-TR24, Comp. & Info. Sci. Dept., Ohio State Univ., 1997 1 Phase-Space Nonlinear Control Toolbox: The Maglev Experience Feng Zhao Shiou C. Loh Jeff A. May Department of Computer and Information Science The Ohio State University Columbus, OH 43210 April 1997
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR28.ps.gz, 19970506 A Certificate Path Generation Algorithm for Authenticated Signaling in ATM Networks Jun Xu Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 fjun,singhalg@cis.ohio-state.edu
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR29.ps.gz, 19970513 Once-and-Forall Management Protocol (OFMP) Sandeep S. Kulkarni Anish Arora Department of Computer and Information Science 1 The Ohio State University Columbus, OH 43210 USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR09.ps.gz, 19970516 Hybrid Algorithms for Complete Exchange in 2D Meshes N. S. Sundar D. N. Jayasimhay 1 D. K. Panda P. Sadayappan Dept. of Computer & Information Science yIntel Corporation, MS RN2-02 The Ohio State University 2200 Mission College Blvd Columbus, OH 43210 Santa Clara, CA 95052-8119
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR30.ps.gz, 19970522 Performance Study of Real-Time Scheduling Techniques under Multicasting Traffic in an ATM Multiplexer Khalid H. Sheta and Mukesh Singhal Department of Computer and Information Science The Ohio State University Columbus, OH 43210 email: sheta@cis.ohio-state.edu, singhal@cis.ohio-state.edu Phone:
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR31.ps.gz, 19970604 A Multiple Layered Signature Database Architecture for Mobile and Internet Environments Yuping Yang, Mukesh Singhal Department of Computer and Information Science, The Ohio State University Columbus, OH 43210 fyangy,singhalg@cis.ohio-state.edu May 27, 1997
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR32.ps.gz, 19970610 Compositional Design of Multitolerant Repetitive Byzantine Agreement 1 Sandeep S. Kulkarni Anish Arora Department of Computer and Information Science The Ohio State University Columbus, OH 43210 USA
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR34.ps.gz, 19970703 Fine-Grain Multitolerant Barrier Synchronization Sandeep S. Kulkarni Anish Arora Department of Computer and Information Science 1 The Ohio State University Columbus, OH 43210 USA
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/fry.nmech.ps.Z, 19970717 Neural Mechanics Robert L. Fry The Johns Hopkins University/Applied Physics Laboratory Laurel, MD USA 20723-6099 robert_fry@jhuapl.edu
	ftp://ftp.cis.ohio-state.edu/pub/neuroprose/peterson.rout.ps.Z, 19970717 LU TP 97-2 March 6, 1997 A Potts Neuron Approach to Communication Routing Jari H akkinen1, Martin Lagerholm2, Carsten Peterson3 and Bo S oderberg4 Complex Systems Group, Department of Theoretical Physics University of Lund, S olvegatan 14A, SE-223 62 Lund, Sweden Submitted to Neural Computation
	ftp://ftp.cis.ohio-state.edu/pub/tech-report/1997/TR35.ps.gz, 19970717 Simulation of Modern Parallel Systems: A CSIM-Based Approach Dhabaleswar K. Panda, Debashis Basak , Donglai Dai, Ram Kesavan, Rajeev Sivaram, Mohammad Banikazemi and Vijay Moorthy Department of Computer and Information Science The Ohio State University Columbus, OH - 43210-1277 July 16, 1997