Hopfield model associative memory with nonzero-diagonal terms in memory matrix

Gene R. Gindi, Arthur F Gmitro, K. Parthasarathy

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

The discrete-valued neural network proposed by Hopfield requires zero-diagonal terms in the memory matrix so that the net evolves toward a local minimum of an energy function. For a version of this model with bipolar nodes and positive terms along the diagonal, the net evolves so that only updates that lower the energy by a sufficient amount are accepted. For a net programmed as an outer-product associative content-addressable memory, the version with nonzero-diagonal elements performs nearly identically to one with zero-diagonal terms, and the dropping of the zero-diagonal requirement is advantageous for optical implementation.

Original languageEnglish (US)
Pages (from-to)129-134
Number of pages6
JournalApplied Optics
Volume27
Issue number1
DOIs
StatePublished - 1988
Externally publishedYes

Fingerprint

Associative storage
associative memory
Neural networks
Data storage equipment
matrices
requirements
energy
products

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

Hopfield model associative memory with nonzero-diagonal terms in memory matrix. / Gindi, Gene R.; Gmitro, Arthur F; Parthasarathy, K.

In: Applied Optics, Vol. 27, No. 1, 1988, p. 129-134.

Research output: Contribution to journalArticle

Gindi, Gene R. ; Gmitro, Arthur F ; Parthasarathy, K. / Hopfield model associative memory with nonzero-diagonal terms in memory matrix. In: Applied Optics. 1988 ; Vol. 27, No. 1. pp. 129-134.
@article{5aa3a9f8adcb4cffb62026c87363dddc,
title = "Hopfield model associative memory with nonzero-diagonal terms in memory matrix",
abstract = "The discrete-valued neural network proposed by Hopfield requires zero-diagonal terms in the memory matrix so that the net evolves toward a local minimum of an energy function. For a version of this model with bipolar nodes and positive terms along the diagonal, the net evolves so that only updates that lower the energy by a sufficient amount are accepted. For a net programmed as an outer-product associative content-addressable memory, the version with nonzero-diagonal elements performs nearly identically to one with zero-diagonal terms, and the dropping of the zero-diagonal requirement is advantageous for optical implementation.",
author = "Gindi, {Gene R.} and Gmitro, {Arthur F} and K. Parthasarathy",
year = "1988",
doi = "10.1364/AO.27.000129",
language = "English (US)",
volume = "27",
pages = "129--134",
journal = "Applied Optics",
issn = "1559-128X",
publisher = "The Optical Society",
number = "1",

}

TY - JOUR

T1 - Hopfield model associative memory with nonzero-diagonal terms in memory matrix

AU - Gindi, Gene R.

AU - Gmitro, Arthur F

AU - Parthasarathy, K.

PY - 1988

Y1 - 1988

N2 - The discrete-valued neural network proposed by Hopfield requires zero-diagonal terms in the memory matrix so that the net evolves toward a local minimum of an energy function. For a version of this model with bipolar nodes and positive terms along the diagonal, the net evolves so that only updates that lower the energy by a sufficient amount are accepted. For a net programmed as an outer-product associative content-addressable memory, the version with nonzero-diagonal elements performs nearly identically to one with zero-diagonal terms, and the dropping of the zero-diagonal requirement is advantageous for optical implementation.

AB - The discrete-valued neural network proposed by Hopfield requires zero-diagonal terms in the memory matrix so that the net evolves toward a local minimum of an energy function. For a version of this model with bipolar nodes and positive terms along the diagonal, the net evolves so that only updates that lower the energy by a sufficient amount are accepted. For a net programmed as an outer-product associative content-addressable memory, the version with nonzero-diagonal elements performs nearly identically to one with zero-diagonal terms, and the dropping of the zero-diagonal requirement is advantageous for optical implementation.

UR - http://www.scopus.com/inward/record.url?scp=84975553564&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975553564&partnerID=8YFLogxK

U2 - 10.1364/AO.27.000129

DO - 10.1364/AO.27.000129

M3 - Article

AN - SCOPUS:84975553564

VL - 27

SP - 129

EP - 134

JO - Applied Optics

JF - Applied Optics

SN - 1559-128X

IS - 1

ER -