Edinburgh Research Explorer

Symbolic knowledge encoding using a dynamic binding mechanism and an embedded inference mechanism

Research output: Chapter in Book/Report/Conference proceedingChapter

Related Edinburgh Organisations

Original languageEnglish
Title of host publicationOscillations in Neural Systems
EditorsD. Levine, B. Brown, T. Shirey
PublisherLawrence Erlbaum Associates
Number of pages26
ISBN (Print)0-8058-2066-3
Publication statusPublished - 1999


This chapter describes how synchronous activity between neuron elements can be used to build a dynamic binding mechanism and knowledge encoding mechanisms in a connectionist manner. The purpose of these mechanisms is to build a connectionist inference architecture that can replicate common symbolic styles of inference. To build such an inference architecture, an extended temporal synchrony approach (Park, Robertson, & Stenning, 1995) is used as a basic building block. This is a revision and extension of an approach to the dynamic binding problem in the connectionist systems, proposed by Shastri and Ajjanagadde (1993). In addition, we introduce a set of algorithms that gives us a means of compiling a class of symbolic rules into a uniform inference network called a structured predicate network. This is used as a connectionist knowledge encoding mechanism which encodes symbolic rules and supports very fast inference.

ID: 3506575