Hybrid Connectionist-Symbolic Models:

a report from the IJCAI'95 workshop on

connectionist-symbolic integration

Ron Sun

Department of Computer Science

The University of Alabama

Tuscaloosa, AL 35487

March 25, 1996

Acknowledgement: I wish to thank Frederic Alexandre, Michael Dyer, John Barnden, Larry Bookman, Noel Sharkey, Jim Hendler, and other members of the committee for their roles in organizing this workshop.

Introduction

The IJCAI Workshop on Connectionist-Symbolic Integration: From Unified to Hybrid Approaches was held for two days during August 19-20 in Montreal, Canada, in conjunction with the fourteenth International Joint Conference on Artificial Intelligence (IJCAI'95). The workshop was co-chaired by Ron Sun and Frederic Alexandre. It featured 23 presentations, including two invited talks, and two panel discussions.

During the two days of the workshop, various presentations and discussions brought to light many new ideas, controversies, and syntheses. The focus was on learning and architectures that feature hybrid representations and support hybrid learning. It was a general consensus among the workshop participants that hybrid connectionist-symbolic models constitute a promising avenue toward developing more robust, more powerful, and more versatile architectures both for cognitive modeling and for intelligent systems. The need for such models has been slowly but steadily growing over the past 5 years. Some new, important approaches have been proposed and developed, some of which were presented at the workshop. In sum, the participants felt that it is definitely worthwhile further pursuing research in this area, which might generate important new ideas and significant new applications in the near future.

The basic motivations for research in hybrid connectionist-symbolic models need to be articulated and made clear. These motivations can be briefly summarized as