Overcoming Rule-Based Rigidity and Connectionist Limitations through Massively-Parallel Case-Based Reasoning

Abstract Symbol manipulation as used in traditional Artificial Intelligence has been criticized by neural net researchers for being excessively inflexible and sequential. On the other hand, the application of neural net techniques to the types of high-level cognitive processing studied in traditional artificial intelligence presents major problems as well. We claim that a promising way out of this impasse is to build neural net models that accomplish massively parallel case-based reasoning. Case-based reasoning, which has received much attention recently, is essentially the same as analogy-based reasoning, and avoids many of the problems leveled at traditional artificial intelligence. Further problems are avoided by doing many strands of case-based reasoning in parallel, and by implementing the whole system as a neural net. In addition, such a system provides an approach to some aspects of the problems of noise, uncertainty and novelty in reasoning systems. We are accordingly modifying our current neural net system (Conposit), which performs standard rule-based reasoning, into a massively parallel case-based reasoning version.

[1]  P. Smolensky.  THE CONSTITUENT STRUCTURE OF CONNECTIONIST MENTAL STATES: A REPLY TO FODOR AND PYLYSHYN , 2010 .

[2]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[3]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[4]  Paul Thagard,et al.  Analogical Mapping by Constraint Satisfaction , 1989, Cogn. Sci..

[5]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[6]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[7]  Thomas A. Standish.  Data Structure Techniques , 1980 .

[8]  David S. Touretzky,et al.  A distributed connectionist representation for concept structures , 1987 .

[9]  J. Barnden,et al.  Winner-take-all networks: Time-based versus activation-based mechanisms for various selection goals , 1990, IEEE International Symposium on Circuits and Systems.

[10]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[11]  W. Freeman.  Second Commentary: On the proper treatment of connectionism by Paul Smolensky (1988) - Neuromachismo Rekindled , 1989 .

[12]  Smadar T. Kedar-Cabelli,et al.  Analogy — From a Unified Perspective , 1988 .

[13]  James L. McClelland,et al.  On learning the past-tenses of English verbs: implicit rules or parallel distributed processing , 1986 .

[14]  John A. Barnden.  Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning , 1989, IJCAI.

[15]  John A. Barnden,et al.  Encoding techniques for complex information structures in connectionist systems , 1991 .

[16]  Lawrence A Birnbaum.  Complex features in planning and understanding: Problems and opportunities for connectionism: Volume 1: High-Level Connectionist Models , 1991 .

[17]  J. Fodor,et al.  Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.