Observation of positive Lyapunov exponent induced by gain increase of neuron nonlinearity in complex-valued associative memories

Author

Hirose, A. ; Onishi, H.

Author_Institution

Res. Center for Adv. Sci. & Technol., Tokyo Univ., Japan

Volume

32

Issue

8

fYear

1996

fDate

4/11/1996 12:00:00 AM

Firstpage

745

Lastpage

746

Abstract

A positive Lyapunov exponent is observed in complex-valued associative memories having dynamical attractors, when a small-signal gain of neuron nonlinearity is increased. When the gain is small, the Lyapunov exponent is constantly zero (normal behaviour). However, it is found in the experiment that, unlike conventional (real-valued) associative memories, the Lyapunov exponent becomes distinctly positive (chaotic behaviour) for a larger neuron gain even if the weighting factors are unchanged. This result suggests that the gain of nonlinear devices has a critical significance on information processing stability in future coherent neural networks

Keywords

Lyapunov methods; chaos; content-addressable storage; neural nets; stability; chaotic behaviour; coherent neural networks; complex-valued associative memories; dynamical attractors; gain increase; information processing stability; neuron nonlinearity; nonlinear device gain; positive Lyapunov exponent; small-signal gain; weighting factors;

fLanguage

English

Journal_Title

Electronics Letters

Publisher

iet

ISSN

0013-5194

Type

jour

DOI

10.1049/el:19960472

Filename

491066