Analog implementation of a 'neural' optimization network

M. T. Musavi, Asim Roy

Research output: Contribution to journalArticle

Abstract

An analog implementation of a neural network has been developed. The circuit is constructed of discrete analog devices. It utilizes a neuron model with graded response property to solve optimization problems. The neuron, which has symmetric synaptic connections, is based on the Hopfield model. The model uses the collective computation properties of analog processor networks. The architecture of the electronic circuitry consists of a highly interconnected network of processing elements, where each processing element is an amplifier to model the firing of a neuron and has an inverted and non-inverted output to enable both excitary and inhibitory connections. The interconnection is of resistive nature.

Original languageEnglish (US)
Pages (from-to)395
Number of pages1
JournalNeural Networks
Volume1
Issue number1 SUPPL
DOIs
StatePublished - 1988
Externally publishedYes

Fingerprint

Neurons
Processing
Equipment and Supplies
Neural networks
Networks (circuits)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

Analog implementation of a 'neural' optimization network. / Musavi, M. T.; Roy, Asim.

In: Neural Networks, Vol. 1, No. 1 SUPPL, 1988, p. 395.

Research output: Contribution to journalArticle

Musavi, M. T. ; Roy, Asim. / Analog implementation of a 'neural' optimization network. In: Neural Networks. 1988 ; Vol. 1, No. 1 SUPPL. pp. 395.
@article{d63515a087914d178f8bc8f0c976f628,
title = "Analog implementation of a 'neural' optimization network",
abstract = "An analog implementation of a neural network has been developed. The circuit is constructed of discrete analog devices. It utilizes a neuron model with graded response property to solve optimization problems. The neuron, which has symmetric synaptic connections, is based on the Hopfield model. The model uses the collective computation properties of analog processor networks. The architecture of the electronic circuitry consists of a highly interconnected network of processing elements, where each processing element is an amplifier to model the firing of a neuron and has an inverted and non-inverted output to enable both excitary and inhibitory connections. The interconnection is of resistive nature.",
author = "Musavi, {M. T.} and Asim Roy",
year = "1988",
doi = "10.1016/0893-6080(88)90421-2",
language = "English (US)",
volume = "1",
pages = "395",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "1 SUPPL",

}

TY - JOUR

T1 - Analog implementation of a 'neural' optimization network

AU - Musavi, M. T.

AU - Roy, Asim

PY - 1988

Y1 - 1988

N2 - An analog implementation of a neural network has been developed. The circuit is constructed of discrete analog devices. It utilizes a neuron model with graded response property to solve optimization problems. The neuron, which has symmetric synaptic connections, is based on the Hopfield model. The model uses the collective computation properties of analog processor networks. The architecture of the electronic circuitry consists of a highly interconnected network of processing elements, where each processing element is an amplifier to model the firing of a neuron and has an inverted and non-inverted output to enable both excitary and inhibitory connections. The interconnection is of resistive nature.

AB - An analog implementation of a neural network has been developed. The circuit is constructed of discrete analog devices. It utilizes a neuron model with graded response property to solve optimization problems. The neuron, which has symmetric synaptic connections, is based on the Hopfield model. The model uses the collective computation properties of analog processor networks. The architecture of the electronic circuitry consists of a highly interconnected network of processing elements, where each processing element is an amplifier to model the firing of a neuron and has an inverted and non-inverted output to enable both excitary and inhibitory connections. The interconnection is of resistive nature.

UR - http://www.scopus.com/inward/record.url?scp=0024171789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024171789&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90421-2

DO - 10.1016/0893-6080(88)90421-2

M3 - Article

VL - 1

SP - 395

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 1 SUPPL

ER -