Abstract

The traditional assumption in artificial intelligence (AI) is that most expert knowledge is encoded in the form of rules. We consider the phenomenon of reasoning from memories of specific episodes, however, to be the foundation of an intelligent system, rather than an adjunct to some other reasoning method. This theory contrasts with much of the current work in similarity-based learning, which tacitly assumes that learning is equivalent to the automatic generation of rules, and differs from work on "explanation-based" and "case-based" reasoning in that it does not depend on having a strong domain model.
With the development of new parallel architectures, specifically the Connection Machine® system, the operations necessary to implement this approach to reasoning have become sufficiently fast to allow experimentation. This article describes MBRtalk, an experimental memory-based reasoning system that has been implemented on the Connection Machine, as well as the application of memory-based reasoning to other domains.