Presentation 2003/7/7
Associative Memory by Hop field NN with Chaos Injection
Yoko UWATE, Yoshifumi NISHIO, Tohru IKEGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, many researchers pay their attentions to the phenomena related to the edge of chaos, which is around the border between periodic state and chaotic state. The authors have investigated the performance of the Hopfield Neural Networks solving combinatorial optimization problems when intermittency chaos, which is the phenomenon on the edge of chaos, is inputted to the neurons as noise. By computer simulations, the intermittency chaos has been confirmed to gain better perforamance to escape out of local minima than fully-developed chaos. However, only the results on the combinatorial optimization problems can not conlude that the intermittency chaos has an excellent ability to escape out of local minima of the Hopfield Neural Networks. In this study, the performance of the Hopfield Neural Networks working as an associative memory when intermittency chaos is inputted as noise. By computer simulations, the rate and the speed of the convergence to an embedded pattern are evaluated.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) intermittency chaos / edge of chaos / chaos noise / Hopfield Neural Network / associative memory
Paper # NLP2003-44
Date of Issue

Conference Information
Committee NLP
Conference Date 2003/7/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Associative Memory by Hop field NN with Chaos Injection
Sub Title (in English)
Keyword(1) intermittency chaos
Keyword(2) edge of chaos
Keyword(3) chaos noise
Keyword(4) Hopfield Neural Network
Keyword(5) associative memory
1st Author's Name Yoko UWATE
1st Author's Affiliation Dept. of Electrical and Electronic Engineering, Tokushima University()
2nd Author's Name Yoshifumi NISHIO
2nd Author's Affiliation Dept. of Electrical and Electronic Engineering, Tokushima University
3rd Author's Name Tohru IKEGUCHI
3rd Author's Affiliation Dept. of Information and Computer Sciences, Saitama University
Date 2003/7/7
Paper # NLP2003-44
Volume (vol) vol.103
Number (no) 185
Page pp.pp.-
#Pages 6
Date of Issue