Hopfield learning rule with high capacity storage of time-correlated patterns

A Storkey; R Valabregue

doi:10.1049/el:19971233

Hopfield learning rule with high capacity storage of time-correlated patterns

A Storkey^*, R Valabregue

^*Corresponding author for this work

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

Abstract / Description of output

A new local and incremental learning rule is examined for its ability to store patterns from a time series in an attractor neural network. This learning rule has a higher capacity than the Hebb rule, and suffers significantly less capacity loss as the correlation between patterns increases.

Original language	English
Pages (from-to)	1803-1804
Number of pages	2
Journal	Electronics Letters
Volume	33
Issue number	21
DOIs	https://doi.org/10.1049/el:19971233
Publication status	Published - 9 Oct 1997

Keywords / Materials (for Non-textual outputs)

Hopfield neural networks
MEMORY

Access to Document

10.1049/el:19971233

Storkey Valabregue 1994 A Hopefield learning ruleAccepted author manuscript, 107 KB

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=633404&queryText=Hopfield+learning+rule+with+high+capacity+storage+of+time-correlated+patterns&newsearch=true&searchField=Search_All

Cite this

@article{3a2637b9ae54496995d0022701ff7a82,

title = "Hopfield learning rule with high capacity storage of time-correlated patterns",

abstract = "A new local and incremental learning rule is examined for its ability to store patterns from a time series in an attractor neural network. This learning rule has a higher capacity than the Hebb rule, and suffers significantly less capacity loss as the correlation between patterns increases.",

keywords = "Hopfield neural networks, MEMORY",

author = "A Storkey and R Valabregue",

year = "1997",

month = oct,

day = "9",

doi = "10.1049/el:19971233",

language = "English",

volume = "33",

pages = "1803--1804",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "Institution of Engineering and Technology",

number = "21",

}

TY - JOUR

T1 - Hopfield learning rule with high capacity storage of time-correlated patterns

AU - Storkey, A

AU - Valabregue, R

PY - 1997/10/9

Y1 - 1997/10/9

N2 - A new local and incremental learning rule is examined for its ability to store patterns from a time series in an attractor neural network. This learning rule has a higher capacity than the Hebb rule, and suffers significantly less capacity loss as the correlation between patterns increases.

AB - A new local and incremental learning rule is examined for its ability to store patterns from a time series in an attractor neural network. This learning rule has a higher capacity than the Hebb rule, and suffers significantly less capacity loss as the correlation between patterns increases.

KW - Hopfield neural networks

KW - MEMORY

U2 - 10.1049/el:19971233

DO - 10.1049/el:19971233

M3 - Article

SN - 0013-5194

VL - 33

SP - 1803

EP - 1804

JO - Electronics Letters

JF - Electronics Letters

IS - 21

ER -

Hopfield learning rule with high capacity storage of time-correlated patterns

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this