Effect of connectivity in an associative memory model

János Komlós; Ramamohan Paturi

doi:10.1016/0022-0000(93)90036-V

Effect of connectivity in an associative memory model

János Komlós, Ramamohan Paturi

School of Arts and Sciences, Mathematics

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

15 Scopus citations

Abstract

We investigate how geometric properties translate into functional properties in sparse networks of computing elements. Specifically, we determine how the eigenvalues of the interconnection graph (which in turn reflect connectivity properties) relate to the quantities, number of items stored, amount of error-correction, radius of attraction, and rate of convergence, in an associative memory model consisting of a sparse network of threshold elements or neurons.

Original language	English (US)
Pages (from-to)	350-373
Number of pages	24
Journal	Journal of Computer and System Sciences
Volume	47
Issue number	2
DOIs	https://doi.org/10.1016/0022-0000(93)90036-V
State	Published - 1993

All Science Journal Classification (ASJC) codes

Theoretical Computer Science
Computer Networks and Communications
Computational Theory and Mathematics
Applied Mathematics

Access to Document

10.1016/0022-0000(93)90036-V

Cite this

@article{ac3d23a3e4a8429599f0617ad38c53cd,

title = "Effect of connectivity in an associative memory model",

abstract = "We investigate how geometric properties translate into functional properties in sparse networks of computing elements. Specifically, we determine how the eigenvalues of the interconnection graph (which in turn reflect connectivity properties) relate to the quantities, number of items stored, amount of error-correction, radius of attraction, and rate of convergence, in an associative memory model consisting of a sparse network of threshold elements or neurons.",

author = "J{\'a}nos Koml{\'o}s and Ramamohan Paturi",

note = "Funding Information: partially supported by the Hungarian National Foundation for Scientitic Research # 1905.",

year = "1993",

doi = "10.1016/0022-0000(93)90036-V",

language = "English (US)",

volume = "47",

pages = "350--373",

journal = "Journal of Computer and System Sciences",

issn = "0022-0000",

publisher = "Academic Press Inc.",

number = "2",

}

TY - JOUR

T1 - Effect of connectivity in an associative memory model

AU - Komlós, János

AU - Paturi, Ramamohan

N1 - Funding Information: partially supported by the Hungarian National Foundation for Scientitic Research # 1905.

PY - 1993

Y1 - 1993

N2 - We investigate how geometric properties translate into functional properties in sparse networks of computing elements. Specifically, we determine how the eigenvalues of the interconnection graph (which in turn reflect connectivity properties) relate to the quantities, number of items stored, amount of error-correction, radius of attraction, and rate of convergence, in an associative memory model consisting of a sparse network of threshold elements or neurons.

AB - We investigate how geometric properties translate into functional properties in sparse networks of computing elements. Specifically, we determine how the eigenvalues of the interconnection graph (which in turn reflect connectivity properties) relate to the quantities, number of items stored, amount of error-correction, radius of attraction, and rate of convergence, in an associative memory model consisting of a sparse network of threshold elements or neurons.

UR - http://www.scopus.com/inward/record.url?scp=0011120855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0011120855&partnerID=8YFLogxK

U2 - 10.1016/0022-0000(93)90036-V

DO - 10.1016/0022-0000(93)90036-V

M3 - Article

AN - SCOPUS:0011120855

SN - 0022-0000

VL - 47

SP - 350

EP - 373

JO - Journal of Computer and System Sciences

JF - Journal of Computer and System Sciences

IS - 2

ER -

Effect of connectivity in an associative memory model

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this