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

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 artificiaa 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 paraliel case-based reasoning. Casebased reasoning, which has received much attention recently, is essentially the same as analogybased 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 systeras. We are accordingly modifying our current neural net system (Conposit), which performs standard rulebased reasoning, into a massively parallel case-based reasoning version. t This work has been supported in part by grant AFOSR-88-0215 from the Air Force Office of Scientific Research and grant NAGW-1592 under the hmovative Research Program of the NASA Office of Space Science and Applications.