1992 | |  | On the Problem of Local Minima in Backpropagation - Marco Gori and Alberto Tesi |
| |  | Bayesian Methods for Adaptive Models - D. MacKay |
| |  | Robust trainability of single neurons - K. Höffgen and H. Simon |
| |  | An improved boosting algorithm and its implications on learning complexity - Y. Freund |
| |  | Polynomial time inference of unions of tree pattern languages - H. Arimura, T. Shinohara and S. Otsuki |
| |  | On the Power of Monotonic Language Learning - S. Lange and T. Zeugmann |
| |  | Proving based on similarity - K. Fujita and M. Harao |
| |  | Universal forecasting algorithms - V. Vovk |
| |  | A Learning Criterion for Stochastic Rules - Kenji Yamanishi |
| |  | Polynomial-time identification of very regular languages in the limit - N. Tanida and T. Yokomori |
| |  | Learning in parallel - J. Vitter and J. Lin |
| |  | Learning Elementary Formal Systems - Setsuo Arikawa, Takeshi Shinohara and Akihiro Yamamoto |
| |  | Learning Two-Tiered Descriptions of Flexible Concepts: The POSEIDON System - F. Bergadano, S. Matwin, R. S. Michalski and J. Zhang |
| |  | Universal sequential learning and decisions from individual data sequences - N. Merhav and M. Feder |
| |  | Inductive inference of formal languages from positive data enumerated primitive-recursively - A. Sakurai |
| |  | Learning Probabilistic Automata and Markov Chains via Queries - Wen-Guey Tzeng |
| |  | Learning semilinear sets from examples and via queries - Yuji Takada |
| |  | A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments - José Del R. Millán and Carme Torras |
| |  | Learning effect of a dynamic thesaurus in associated information retrieval - H. Kimoto and T. Iwadera |
| |  | The Design and Analysis of Efficient Learning Algorithms - R. E. Schapire |
| |  | Learning Boolean read-once formulas with arbitrary symmetric and constant fan-in gates - N. H. Bshouty, T. R. Hancock and L. Hellerstein |
| |  | Recovery from multiple faults in relational theory - S. Tangkitvanich and M. Shimura |
| |  | Transfer of Learning by Composing Solutions of Elemental Sequential Tasks - Satinder Pal Singh |
| |  | Relationships between PAC-learning algorithms and weak Occam algorithms - E. Takimoto and A. Maruoka |
| |  | On uniform learnability of language families - S. Kapur and G. Bilardi |
| |  | Entropy Optimization Principles with Applications - J. N. Kapur and H. K Kesavan |
| |  | Knowledge-intensive learning in connectionist networks - A. Namatame |
| |  | On Learning Limiting Programs - J. Case, S. Jain and A. Sharma |
| |  | Degrees of inferability - P. Cholak, R. Downey, L. Fortnow, W. Gasarch, E. Kinber, M. Kummer, S. Kurtz and T. Slaman |
| |  | Query by committee - H. S. Seung, M. Opper and H. Sompolinsky |
| |  | Learning switching concepts - A. Blum and P. Chalasani |
| |  | Case based learning in inductive inference - K. P. Jantke |
| |  | Learning conjunctions of Horn clauses - D. Angluin, M. Frazier and L. Pitt |
| |  | On the role of equivalence quries in MAT learning - S. Tani |
| |  | A noise model on learning sets of strings - Y. Sakakibara and R. Siromoney |
| |  | Random DFA's can be approximately learned from sparse uniform examples - K. J. Lang |
| |  | Analogy is NP-hard - S. Furuya and S. Miyano |
| |  | Too Much Information Can be too Much for Efficient Learning - R. Wiehagen and T. Zeugmann |
| |  | Learning recursive languages with bounded mind changes - S. Lange and T. Zeugmann |
| |  | On the Study of First Language Acquisition - D. Osherson and S. Weinstein |
| |  | Learning with a slowly changing distribution - P. L. Bartlett |
| |  | Practical Issues in Temporal Difference Learning - Gerald Tesauro |
| |  | Dynamic Parameter Encoding for Genetic Algorithms - Nicol N. Schraudolph and Richard K. Belew |
| |  | Computational learning theory: survey and selected bibliography - D. Angluin |
| |  | A training algorithm for optimal margin classifiers - B. E. Boser, I. M. Guyon and V. N. Vapnik |
| |  | Reconstructing algebraic functions from mixed data - S. Ar, R. J. Lipton, R. Rubinfeld and M. Sudan |
| |  | Characterizations of learnability for classes of { 0,dots ,n }-valued functions - S. Ben-David, N. Cesa-Bianchi and P. M. Long |
| |  | A computational model of teaching - J. Jackson and A. Tomkins |
| |  | Characterization of pattern languages - Y. Mukouchi |
| |  | Fast Learning of k-term DNF Formulas with Queries - A. Blum and S. Rudich |
| |  | A Bayesian Method for the Induction of Probabilistic Networks from Data - Gregory F. Cooper and Edward Herskovits |
| |  | PAC-learnability of determinate logic programs - S. Dzeroski, S. Muggleton and S. Russell |
| |  | A Universal Method of Scientific Inquiry - Daniel N. Osherson, Michael Stob and Scott Weinstein |
| |  | Self-Improving Reactive Agents Based On Reinforcement Learning, Planning and Teaching - Long-ji Lin |
| |  | Learning non-parametric densities by finite-dimensional parametric hypotheses - K. Yamanishi |
| |  | Four Types of Learning Curves - S. Amari, N. Fujita and S. Shinomoto |
| |  | Computational Learning Theory - M. Anthony and N. Biggs |
| |  | Learning programs with an easy to calculate set of errors - W. I. Gasarch, R. K. Sitaraman, C. H. Smith and M. Velauthapillai |
| |  | ACE: a syntax-directed editor customizable from examples and queries - Y. Takada, Y. Sakakibara and T. Ohtani |
| |  | Explorations of an Incremental, Bayesian Algorithm for Categorization - John R. Anderson and Michael Matessa |
| |  | Corrigendum to Types of noise in data for concept learning - R. H. Sloan |
| |  | Higher-Order and Modal Logic as a Framework for Explanation-Based Generalization - Scott Dietzen and Frank Pfenning |
| |  | A form of analogy as an abductive inference - M. Haraguchi |
| |  | On the sample complexity of PAC-learning using random and chosen examples - B. B. Eisenberg |
| |  | Learning in multi-agent environments - P. Brazdil |
| |  | Analogical reasoning as a form of hypothetical reasoning and justification-based knowledge acquisition - R. Orihara |
| |  | The learning complexity of smooth functions of a single variable - D. Kimber and P. Long |
| |  | Lower Bound Methods and Separation Results for On-Line Learning Models - Wolfgang Maass and György Turán |
| |  | Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning - Ronald J. Williams |
| |  | On learning noisy theshold functions with finite precision weights - R. Meir and J. F. Fontanari |
| |  | A Statistical Approach to Solving the EBL Utility Problem - Russell Greiner and Igor Jurišica |
| |  | Inductive Inference from Theory Laden Data - K. T. Kelly and C. Glymour |
| |  | Improving Performance in Neural Networks Using a Boosting Algorithm - H. Drucker, R. Schapire and P. Simard |
| |  | A Reply to Honavar's Book Review of Neural Network Design and the Complexity of Learning - J. Stephen Judd |
| |  | A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training - L. K. Jones |
| |  | Which classes of elementary formal systems are polynomial-time learnable? - S. Miyano, A. Shinohara and T. Shinohara |
| |  | Preliminary study on program synthesis based on induction and verification - K. Furukawa |
| |  | A Unifying Approach to Monotonic Language Learning on Informant - S. Lange and T. Zeugmann |
| |  | Learning heirarchical rule sets - J. Kivinen, H. Mannila and E. Ukkonen |
| |  | A Machine Discovery from Amino Acid Sequences by Decision Trees over Regular Patterns - Setsuo Arikawa, Satoru Kuhara, Satoru Miyano, Yasuhito Mukouchi, Ayumi Shinohara and Takeshi Shinohara |
| |  | Preservation of predictability under polynomially sparse variations and its applications - N. Abe |
| |  | Abductive Explanation-Based Learning: A Solution to the Multiple Inconsistent Explanation Problem - William W. Cohen |
| |  | Learnability of description logics - W. W. Cohen and H. Hirsh |
| |  | Polynomial time inference of a subclass of context-free transformations - H. Arimura, H. Ishizaka and T. Shinohara |
| |  | Efficient learning of context-free grammars from positive structural examples - Yasubumi Sakakibara |
| |  | Memory Limited Inductive Inference Machines - Rusins Freivalds and Carl Smith |
| |  | On the Necessity of Occam Algorithms - Raymond Board and Leonard Pitt |
| |  | Learning k-term DNF formulas with an incomplete membership oracle - S. A. Goldman and H. D. Mathias |
| |  | On exact specification by examples - M. Anthony, G. Brightwell, D. Cohen and J. Shawe-Taylor |
| |  | Learning Integer Lattices - D. Helmbold, R. Sloan and M. K. Warmuth |
| |  | Universal Prediction of Individual Sequences - M. Feder, N. Merhav and M. Gutman |
| |  | Prequential Analysis, Stochastic Complexity and Bayesian Inference - A. P. Dawid |
| |  | Learning simple Boolean concepts - N. Littlestone |
| |  | A knowledge transfer model: from zero-knowledge toward full knowledge - Y. Tsukada and K. Koyama |
| |  | Some weak learning results - D. P. Helmbold and M. K. Warmuth |
| |  | Aggregating Inductive Expertise on Partial Recursive Functions - Anna-Maria Emde and Britta Schinzel |
| |  | On learning ring-sum expansions - P. Fischer and H. Simon |
| |  | Read-thrice DNF is hard to learn with membership and equivalence queries - H. Aizenstein, L. Hellerstein and L. Pitt |
| |  | A Framework for Average Case Analysis of Conjunctive Learning Algorithms - Michael J. Pazzani and Wendy Sarrett |
| |  | Algorithmic Learning Theory with Elementary Formal Systems - Setsuo Arikawa, Satoru Miyano, Ayumi Shinohara, Takeshi Shinohara and Akihiro Yamamoto |
| |  | PAB-decisions for Boolean and real-valued features - S. Anoulova, P. Fischer, S. Pölt and H. U. Simon |
| |  | On the exact learning of formulas in parallel - N. H. Bshouty and R. Cleve |
| |  | A technique for upper bounding the spectral norm with applications to learning - M. Bellare |
| |  | Inductive Inference From All Positive and Some Negative Data - T. Motoki |
| |  | On the Computational Complexity of Approximating Distributions by Probabilistic Automata - Naoki Abe and Manfred K. Warmuth |
| |  | Cryptographic lower bounds on learnability of Boolean functions on the uniform distribution - M. Kharitonov |
| |  | Polynomial uniform convergence and polynomial-sample learnability - A. Bertoni, P. Campadelli, A. Morpurgo and S. Panizza |
| |  | A Comparison between Squared Error and Relative Entropy Metrics Using Several Optimization Algorithms - R. L. Watrous |
| |  | The logic of molecular geneticists for the understanding of genetic information - Y. Sakaki |
| |  | Towards a more comprehensive theory of learning in computers - P. M. Long |
| |  | Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory - David Haussler |
| |  | The Utility of Knowledge in Inductive Learning - Michael Pazzani and Dennis Kibler |
| |  | A Further Comparison of Splitting Rules for Decision-Tree Induction - Wray Buntine and Tim Niblett |
| |  | Exact learning of read-k disjoint DNF and not-so-disjoint DNF - H. Aizenstein and L. Pitt |
| |  | Generalization versus classification - R. Wiehagen and C. H. Smith |
| |  | Absolute error bounds for learning linear functions online - E. J. Bernstein |
| |  | PAC learning with generalized samples and an application to stochastic geometry - S. R. Kulkarni, S. K. Mitter, J. N. Tsitsiklis and O. Zeitouni |
| |  | Inferring regular languages in polynomial update time - J. Oncina and P. Garcia |
| |  | Towards learning by abstraction - S. Sakurai and M. Haraguchi |
| |  | Learning DNF formulae under classes of probability distributions - M. Flammini, A. Marchetti-Spaccamela and L. K. Cera |
| |  | Neural Network Design and the Complexity of Learning - Vasant Honavar |
| |  | Characterization of finite identification - Y. Mukouchi |
| |  | Inductive reasoning and Kolmogorov complexity - M. Li and P. Vitanyi |
| |  | The use of abstract primitives in representing the meaning of Verbs for understanding metaphors - M. Suwa and H. Motoda |
| |  | Inductive inferability for formal languages from positive data - M. Sato and K. Umayahara |
| |  | Learning stochastic functions by smooth simultaneous estimation - K. L. Buescher and P. R. Kumar |
| |  | Types of monotonic language learning and their characterization - S. Lange and T. Zeugmann |
| |  | Learning arithmetic read-once formulas - N. H. Bshouty, T. R. Hancock and L. Hellerstein |
| |  | Analogical reasoning using elementary formal system with mismatch - T. Miyahara |
| |  | Dominating distributions and learnability - G. M. Benedek and A. Itai |
| |  | An interactive knowledge transfer model and analysis of Mastermind game - K. Koyama and T. Lai |
| |  | Forward models: Supervised learning with a distal teacher - M. I. Jordan and D. E. Rumelhart |
| |  | On-line learning of rectangles - Z. Chen and W. Maass |
| |  | Interactive Concept-Learning and Constructive Induction by Analogy - Luc De Raedt and Maurice Bruynooghe |
| |  | On the Handling of Continuous-Valued Attributes in Decision Tree Generation - Usama M. Fayyad and Keki B. Irani |
| |  | Apple tasting and nearly one-sided learning - D. P. Helmbold, N. Littlestone and P. M. Long |
| |  | Machine Learning: A Maturing Field - Jaime Carbonell |
| |  | A logical analysis of relevance in analogy - J. Arima |
| |  | Technical Note Q-Learning - Christopher J. C. H. Watkins and Peter Dayan |
| |  | The Convergence of TD(lambda) for General lambda - Peter Dayan |
| |  | Implementing Valiant's Learnability Theory Using Random Sets - E. M. Oblow |
| |  | BELLMAN STRIKES AGAIN! The growth rate of sample complexity with dimension for the nearest neighbor classifier - S. S. Venkatesh, R. R. Snapp and D. Psaltis |
| |  | Approximate testing and learnability - K. Romanik |
| |  | Learning from Multiple Sources of Inaccurate Data - G. Baliga, S. Jain and A. Sharma |
| |  | Polynomial time learning with version spaces - Haym Hirsh |
| |  | Incrementally Learning Time-Varying Half-planes - T. P. Anthony Kuh and R. L. Rivest |
| |  | Language learning from stochastic input - S. Kapur and G. Bilardi |
| |  | First Nearest Neighbor Classification on Frey and Slate's Letter Recognition Problem - Terence C. Fogarty |
| |  | Strong Separation of Learning Classes - J. Case, K. J. Chen and S. Jain |
| |  | Discrimination-Based Constructive Induction of Logic Programs - Boonserm Kijsirikul, Masayuki Numao and Masamichi Shimura |
| January |  | Inferring Graphs from Walks - J. A. Aslam |
| February |  | Connectionist Modeling and Control of Finite-State Environments - J. R. Bachrach |
| |  | Algorithms for Exploring an Unknown Graph - M. Betke |
| March |  | Identifiability of Hidden Markov Information Sources and their Minimum Degrees of Freedom - H. Ito, S. Amari and K. Kobayashi |
| |  | Learning via Queries to [+,<] - W. Gasarch, M. Pleszkoch and R. Solovay |
| April |  | Bayesian Training of Backpropagation Networks by the Hybrid Monte Carlo Method - R. M. Neal |
| June |  | Some ideas on learning with directional feedback - I. Barland |
| |  | Probabilistic Hill-Climbing: Theory and Applications - Russell Greiner |
| July |  | Learning via Queries - W. Gasarch and C. H. Smith |
| |  | Polynomially Sparse Variations and Reducibility among prediction problems - N. Abe and O. Watanabe |
| |  | Speeding inference by acquiring new concepts - Henry Kautz and Bart Selman |
| September |  | Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications - D. Haussler |
| October |  | Learning useful Horn approximations - Russell Greiner and Dale Schuurmans |
| |  | Learning Boolean Functions in an Infinite Attribute Space - A. Blum |
| |  | Analogical and Inductive Inference, International Workshop AII '92. Dagstuhl Castle, Germany, October 1992, Proceedings - K. P. Jantke |
| |  | A metric entropy bound is not sufficient for learnability - R. Dudley, S. Kulkarni, T. Richardson and O. Zeituni |
| November |  | Neural Networks in Mathematica - J. A. Freeman |
| December |  | Hinfinity-optimal estimation: A tutorial - U. Shaked and Y. Theodor |