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 Citations (Scopus)

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

Fingerprint

Integrated circuits
Neural networks
Circuit theory
Brain
Hardware

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Rao, A., Walker, M. R., Clark, L. T., & Akers, L. A. (1989). Integrated circuit emulation of ART1 networks. In IEE Conference Publication (313 ed., pp. 37-41). Publ by IEE.

Integrated circuit emulation of ART1 networks. / Rao, Arun; Walker, Mark R.; Clark, L. T.; Akers, L. A.

IEE Conference Publication. 313. ed. Publ by IEE, 1989. p. 37-41.

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

Rao, A, Walker, MR, Clark, LT & Akers, LA 1989, Integrated circuit emulation of ART1 networks. in IEE Conference Publication. 313 edn, Publ by IEE, pp. 37-41, First IEE International Conference on Artificial Neural Networks, London, Engl, 10/16/89.
Rao A, Walker MR, Clark LT, Akers LA. Integrated circuit emulation of ART1 networks. In IEE Conference Publication. 313 ed. Publ by IEE. 1989. p. 37-41
Rao, Arun ; Walker, Mark R. ; Clark, L. T. ; Akers, L. A. / Integrated circuit emulation of ART1 networks. IEE Conference Publication. 313. ed. Publ by IEE, 1989. pp. 37-41
@inproceedings{d7aecf794da244c89b004f33a5e52b32,
title = "Integrated circuit emulation of ART1 networks",
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.",
author = "Arun Rao and Walker, {Mark R.} and Clark, {L. T.} and Akers, {L. A.}",
year = "1989",
language = "English (US)",
pages = "37--41",
booktitle = "IEE Conference Publication",
publisher = "Publ by IEE",
edition = "313",

}

TY - GEN

T1 - Integrated circuit emulation of ART1 networks

AU - Rao, Arun

AU - Walker, Mark R.

AU - Clark, L. T.

AU - Akers, L. A.

PY - 1989

Y1 - 1989

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0024911453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024911453&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024911453

SP - 37

EP - 41

BT - IEE Conference Publication

PB - Publ by IEE

ER -