Constructing associative memories using neural networks

X. Xu; W. T. Tsai

doi:10.1016/0893-6080(90)90073-T

Constructing associative memories using neural networks

X. Xu, W. T. Tsai

Computing and Augmented Intelligence, School of (IAFSE-SCAI)

Research output: Contribution to journal › Article › peer-review

12 Scopus citations

Abstract

This paper proposes using a generalized Hopfield's model, also known as the McCulloch-Pitts model, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.

Original language	English (US)
Pages (from-to)	301-309
Number of pages	9
Journal	Neural Networks
Volume	3
Issue number	3
DOIs	https://doi.org/10.1016/0893-6080(90)90073-T
State	Published - 1990

Keywords

Associative memory
Memory capacity
Neural network model

ASJC Scopus subject areas

Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/0893-6080(90)90073-T

Cite this

@article{df4d4a1af2f64dc2a9199b48bf8861b0,

title = "Constructing associative memories using neural networks",

abstract = "This paper proposes using a generalized Hopfield's model, also known as the McCulloch-Pitts model, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.",

keywords = "Associative memory, Memory capacity, Neural network model",

author = "X. Xu and Tsai, {W. T.}",

year = "1990",

doi = "10.1016/0893-6080(90)90073-T",

language = "English (US)",

volume = "3",

pages = "301--309",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

number = "3",

}

TY - JOUR

T1 - Constructing associative memories using neural networks

AU - Xu, X.

AU - Tsai, W. T.

PY - 1990

Y1 - 1990

N2 - This paper proposes using a generalized Hopfield's model, also known as the McCulloch-Pitts model, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.

AB - This paper proposes using a generalized Hopfield's model, also known as the McCulloch-Pitts model, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.

KW - Associative memory

KW - Memory capacity

KW - Neural network model

UR - http://www.scopus.com/inward/record.url?scp=0025232994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025232994&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(90)90073-T

DO - 10.1016/0893-6080(90)90073-T

M3 - Article

AN - SCOPUS:0025232994

SN - 0893-6080

VL - 3

SP - 301

EP - 309

JO - Neural Networks

JF - Neural Networks

IS - 3

ER -

Constructing associative memories using neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this