Accession Number : ADA188530

Title :   A Distributed Connectionist Production System.

Descriptive Note : Interim rept.,

Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE

Personal Author(s) : Touretzky, David S ; Hinton, Geoffrey E

PDF Url : ADA188530

Report Date : Dec 1987

Pagination or Media Count : 42

Abstract : DCPS is a connectionist production system interpreter that uses distributed representations. As a connectionist model it consists of many simple, richly interconnected neuron like computing units that cooperate to solve problems in parallel. One motivation for constructing DCPS was to demonstrate that connectionist models are capable of representing and using explicit rules. A second motivation was to show how coarse coding or distributed representations can be used to construct a working memory that requires far fewer units than the number of different facts that can potentially be stored. The simulation we present is intended as a detailed demonstration of the feasibility of certain ideas and should not be viewed as a full implementation of production systems. Our current model only has a few of the many interesting emergent properties that we eventually hope to demonstrate: it is damage resistant, it performs matching and variable binding by massively parallel constraint satisfaction, and the capacity of its working memory is dependent on the similarity of the items being stored.

Descriptors :   *CIRCUIT INTERCONNECTIONS, *NEURAL NETS, CODING, DEMONSTRATIONS, DISTRIBUTION, FEASIBILITY STUDIES, MEMORY DEVICES, MOTIVATION, NERVE CELLS, PRODUCTION, SIMULATION, VARIABLES

Subject Categories : Bionics
      Computer Hardware

Distribution Statement : APPROVED FOR PUBLIC RELEASE