Associative memory neural networks with concatenated vectors and nonzero diagonal terms

Emanuel Marom

doi:10.1016/0893-6080(90)90074-U

Associative memory neural networks with concatenated vectors and nonzero diagonal terms

Emanuel Marom^*

^*Corresponding author for this work

Engineering General

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

3 Scopus citations

Abstract

The effects of vector concatenation as well as that of eliminating the zero diagonal restriction of associative memory neural network matrices is analyzed. Extensive computer simulations seem to indicate that the use of concatenated vectors increases the storage capacity of the association matrices, beyond the accepted practical limit of 0.14N, N being the length of the stored vectors.

Original language	English
Pages (from-to)	311-318
Number of pages	8
Journal	Neural Networks
Volume	3
Issue number	3
DOIs	https://doi.org/10.1016/0893-6080(90)90074-U
State	Published - 1990

Keywords

Associative memories
Error correction
Memory capacity
Neural networks
Nonzero diagonal matrix
Vector concatenation

Access to Document

10.1016/0893-6080(90)90074-U

Cite this

@article{d417d20782f34c039fa8a071ee141337,

title = "Associative memory neural networks with concatenated vectors and nonzero diagonal terms",

abstract = "The effects of vector concatenation as well as that of eliminating the zero diagonal restriction of associative memory neural network matrices is analyzed. Extensive computer simulations seem to indicate that the use of concatenated vectors increases the storage capacity of the association matrices, beyond the accepted practical limit of 0.14N, N being the length of the stored vectors.",

keywords = "Associative memories, Error correction, Memory capacity, Neural networks, Nonzero diagonal matrix, Vector concatenation",

author = "Emanuel Marom",

year = "1990",

doi = "10.1016/0893-6080(90)90074-U",

language = "אנגלית",

volume = "3",

pages = "311--318",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Ltd.",

number = "3",

}

TY - JOUR

T1 - Associative memory neural networks with concatenated vectors and nonzero diagonal terms

AU - Marom, Emanuel

PY - 1990

Y1 - 1990

N2 - The effects of vector concatenation as well as that of eliminating the zero diagonal restriction of associative memory neural network matrices is analyzed. Extensive computer simulations seem to indicate that the use of concatenated vectors increases the storage capacity of the association matrices, beyond the accepted practical limit of 0.14N, N being the length of the stored vectors.

AB - The effects of vector concatenation as well as that of eliminating the zero diagonal restriction of associative memory neural network matrices is analyzed. Extensive computer simulations seem to indicate that the use of concatenated vectors increases the storage capacity of the association matrices, beyond the accepted practical limit of 0.14N, N being the length of the stored vectors.

KW - Associative memories

KW - Error correction

KW - Memory capacity

KW - Neural networks

KW - Nonzero diagonal matrix

KW - Vector concatenation

UR - https://www.scopus.com/pages/publications/0025232995

U2 - 10.1016/0893-6080(90)90074-U

DO - 10.1016/0893-6080(90)90074-U

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0025232995

SN - 0893-6080

VL - 3

SP - 311

EP - 318

JO - Neural Networks

JF - Neural Networks

IS - 3

ER -

Associative memory neural networks with concatenated vectors and nonzero diagonal terms

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this