High Performance Associative Memories and Structured Weight Dilution

S.P. Turvey; S. Hunt; N. Davey; R. Frank

High Performance Associative Memories and Structured Weight Dilution

S.P. Turvey
, S. Hunt
, N. Davey
, R. Frank

Research output: Chapter in Book/Report/Conference proceeding › Chapter

41 Downloads (Pure)

Abstract

The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.

Original language	English
Title of host publication	Applications and Science in Soft Computing - Advances in Intelligent and Soft Computing , Vol. 24
Editors	A. Lotfi, J.M. Garibaldi
Publisher	Springer Nature
Pages	23-30
ISBN (Print)	978-3-540-40856-7
Publication status	Published - 2004

Keywords

Hopfield Networks
Basins of Attraction

Access to Document

102096.pdf

Cite this

@inbook{f3e1e9cc0c8e45a08a263fc03b33427f,

title = "High Performance Associative Memories and Structured Weight Dilution",

abstract = "The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.",

keywords = "Hopfield Networks, Basins of Attraction",

author = "S.P. Turvey and S. Hunt and N. Davey and R. Frank",

note = "Copyright Springer",

year = "2004",

language = "English",

isbn = "978-3-540-40856-7",

pages = "23--30",

editor = "A. Lotfi and J.M. Garibaldi",

booktitle = "Applications and Science in Soft Computing - Advances in Intelligent and Soft Computing , Vol. 24",

publisher = "Springer Nature ",

address = "Netherlands",

}

TY - CHAP

T1 - High Performance Associative Memories and Structured Weight Dilution

AU - Turvey, S.P.

AU - Hunt, S.

AU - Davey, N.

AU - Frank, R.

N1 - Copyright Springer

PY - 2004

Y1 - 2004

N2 - The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.

AB - The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.

KW - Hopfield Networks

KW - Basins of Attraction

M3 - Chapter

SN - 978-3-540-40856-7

SP - 23

EP - 30

BT - Applications and Science in Soft Computing - Advances in Intelligent and Soft Computing , Vol. 24

A2 - Lotfi, A.

A2 - Garibaldi, J.M.

PB - Springer Nature

ER -

High Performance Associative Memories and Structured Weight Dilution

Abstract

Keywords

Access to Document

Fingerprint

Cite this