Integrated circuit emulation of ART1 networks

Arun Rao, Mark R. Walker, L. T. Clark, L. A. Akers

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Adaptive Resonance Theory (ART) is a neural-network based clustering method developed by Carpenter and Grossberg. Its inspiration is neurobiological and its component parts are intended to model a variety of hierarchical inference levels in the human brain. Neural networks based upon ART are capable of the following: (i) 'Recognizing' patterns close to previously stored patterns according to some criterion. (ii) Storing patterns which are not close to already stored patterns. Two varieties of ART networks have been proposed by Carpenter and Grossberg. ART1 (1) recognizes binary inputs and ART2 (2) can deal with general analog inputs as well. Since the emphasis of this work is on conventional hardware implementation, only ART1 will be specifically treated. Many comments, however, apply to either network.

Original languageEnglish (US)
Title of host publicationIEE Conference Publication
PublisherPubl by IEE
Pages37-41
Number of pages5
Edition313
StatePublished - 1989
EventFirst IEE International Conference on Artificial Neural Networks - London, Engl
Duration: Oct 16 1989Oct 18 1989

Other

OtherFirst IEE International Conference on Artificial Neural Networks
CityLondon, Engl
Period10/16/8910/18/89

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Integrated circuit emulation of ART1 networks'. Together they form a unique fingerprint.

Cite this