On permutation symmetries of hopfield model neural network

Discrete Hopfield neural network (DHNN) is studied by performing permutation operations on the synaptic weight matrix. The storable patterns set stored with Hebbian learning algorithm in a network without losing memories is studied, and a condition which makes sure all the patterns of the storable...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiyang Dong, Shenchu Xu, Zhenxiang Chen, Boxi Wu
Format: Article
Language:English
Published: Wiley 2001-01-01
Series:Discrete Dynamics in Nature and Society
Subjects:
Online Access:http://dx.doi.org/10.1155/S1026022601000139
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850225820929359872
author Jiyang Dong
Shenchu Xu
Zhenxiang Chen
Boxi Wu
author_facet Jiyang Dong
Shenchu Xu
Zhenxiang Chen
Boxi Wu
author_sort Jiyang Dong
collection DOAJ
description Discrete Hopfield neural network (DHNN) is studied by performing permutation operations on the synaptic weight matrix. The storable patterns set stored with Hebbian learning algorithm in a network without losing memories is studied, and a condition which makes sure all the patterns of the storable patterns set have a same basin size of attraction is proposed. Then, the permutation symmetries of the network are studied associating with the stored patterns set. A construction of the storable patterns set satisfying that condition is achieved by consideration of their invariance under a point group.
format Article
id doaj-art-5b7b579e47ad486e993f176c6ae6d491
institution OA Journals
issn 1026-0226
1607-887X
language English
publishDate 2001-01-01
publisher Wiley
record_format Article
series Discrete Dynamics in Nature and Society
spelling doaj-art-5b7b579e47ad486e993f176c6ae6d4912025-08-20T02:05:13ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2001-01-016212913610.1155/S1026022601000139On permutation symmetries of hopfield model neural networkJiyang Dong0Shenchu Xu1Zhenxiang Chen2Boxi Wu3Department of Physics, Xiamen University, Xiamen 361005, ChinaDepartment of Physics, Xiamen University, Xiamen 361005, ChinaDepartment of Physics, Xiamen University, Xiamen 361005, ChinaDepartment of Physics, Xiamen University, Xiamen 361005, ChinaDiscrete Hopfield neural network (DHNN) is studied by performing permutation operations on the synaptic weight matrix. The storable patterns set stored with Hebbian learning algorithm in a network without losing memories is studied, and a condition which makes sure all the patterns of the storable patterns set have a same basin size of attraction is proposed. Then, the permutation symmetries of the network are studied associating with the stored patterns set. A construction of the storable patterns set satisfying that condition is achieved by consideration of their invariance under a point group.http://dx.doi.org/10.1155/S1026022601000139Discrete hopfield neural network; Permutation symmetries; Associative memory; Storable patterns set.
spellingShingle Jiyang Dong
Shenchu Xu
Zhenxiang Chen
Boxi Wu
On permutation symmetries of hopfield model neural network
Discrete Dynamics in Nature and Society
Discrete hopfield neural network; Permutation symmetries; Associative memory; Storable patterns set.
title On permutation symmetries of hopfield model neural network
title_full On permutation symmetries of hopfield model neural network
title_fullStr On permutation symmetries of hopfield model neural network
title_full_unstemmed On permutation symmetries of hopfield model neural network
title_short On permutation symmetries of hopfield model neural network
title_sort on permutation symmetries of hopfield model neural network
topic Discrete hopfield neural network; Permutation symmetries; Associative memory; Storable patterns set.
url http://dx.doi.org/10.1155/S1026022601000139
work_keys_str_mv AT jiyangdong onpermutationsymmetriesofhopfieldmodelneuralnetwork
AT shenchuxu onpermutationsymmetriesofhopfieldmodelneuralnetwork
AT zhenxiangchen onpermutationsymmetriesofhopfieldmodelneuralnetwork
AT boxiwu onpermutationsymmetriesofhopfieldmodelneuralnetwork