Symbol Structures in Connectionist Networks: Five Properties and Two Architectures.

摘要

We define five properties of symbol representations (called the Five M's) that together provide a powerful and flexible symbol processing facility. Our ideal symbol structures are Mobile, Memorable, Meaningful, Malleable, and Modifiable. Conventional symbol processing architectures, such as Lisp on von Neumann machines, support some of these properties, but others seem to require flexibility and an ability to generalize that is unique to connectionist models. Two recently-developed connectionist architectures, BoltzCONS and micro-KLONE, are described in some detail. Representations used in these two architectures satisfy different subsets of the Five M's. Artificial intelligence, Connectionism, Symbols, Computer programs, Lisp on vonNeumann machines, BoltzCONS, Micro-kLONE. (jg)