Encoding Techniques for Complex Information Structures in Connectionist Systems

Two general information-encoding techniques called ‘relative-position encoding’ and ‘pattern-similarity association’ are presented and are claimed to be a convenient basis for the connectionist implementation of complex, short-term information processing of the sort needed in commonsense reasoning, semantic/pragmatic interpretation of natural language utterances, and other types of high-level cognitive processing.

Abstract

Two general information-encoding techniques called ‘relative-position encoding’ and ‘pattern-similarity association’ are presented. They are claimed to be a convenient basis for the connectionist implementation of complex, short-term information processing of the sort needed in commonsense reasoning, semantic/pragmatic interpretation of natural language utterances, and other types of high-level cognitive processing. The relationships of the techniques to other connectionist information-structuring methods, and also to methods used in computers, are discussed in detail. The rich interrelationships of these other connectionist and computer methods are also clarified. We detail the particular, simple forms that the relative-position encoding and pattern-similarity association techniques take in our own connectionist system, called Conposit, in order to clarify some issues and to provide evidence that the techniques are indeed useful in practice.