Presentation 2006-12-05
Effects of Dynamical Noise on Chaotic Neural Network Dynamics
Yuhei NIKAIDO, Toshiya IWAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We perform numerical experiments of the auto-associative chaotic neural network model with the dynamical noise for two kinds of stored patterns; one is correlated patterns and another is uncorrelated patterns. Noise effects on dynamical properties are investigated and the following results are obtained. i) Without noise, the parameter space is divided into four kinds of dynamical states. Depending on the correlation among stored patterns, these states emerge and disappear. ii) Dynamical properties such as these states does not seem to depend on noises qualitatively but depend quantitatively, iii) Smoothness of associative frequencies of stored patterns on the parameter space seems to be enhanced by the presence of noise. Reasons for these properties are investigated by the analysis of orbital instabilities.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) chaos / neural network / noise / dynamical associative cognition
Paper # NC2006-86
Date of Issue

Conference Information
Committee NC
Conference Date 2006/11/28(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Effects of Dynamical Noise on Chaotic Neural Network Dynamics
Sub Title (in English)
Keyword(1) chaos
Keyword(2) neural network
Keyword(3) noise
Keyword(4) dynamical associative cognition
1st Author's Name Yuhei NIKAIDO
1st Author's Affiliation Department of Computer Science, College of Engineering, Nihon University()
2nd Author's Name Toshiya IWAI
2nd Author's Affiliation Department of Computer Science, College of Engineering, Nihon University
Date 2006-12-05
Paper # NC2006-86
Volume (vol) vol.106
Number (no) 407
Page pp.pp.-
#Pages 6
Date of Issue