Stability conditions for bi-directional associative memory neural networks with delay

Author

Zhou, Dongming ; Cao, Jinde

Author_Institution

Inf. Coll., Yunnan Univ., Kunming, China

Volume

2

fYear

2000

fDate

2000

Firstpage

809

Abstract

Bi-directional associative memory (BAM) models are two-layer heteroassociative networks. In the paper, the global asymptotic stability is studied for continuous bi-directional associative memory neural networks with axonal signal transmission delay while the neuronal output signal function S is not differentiable and strictly monotone increasing. Several sufficient conditions guaranteeing the network´s global asymptotic stability are derived, the obtained results have important leading significance in the design and application of BAM

Keywords

asymptotic stability; content-addressable storage; delays; multilayer perceptrons; stability criteria; BAM; axonal signal transmission delay; bi-directional associative memory neural networks; delay; global asymptotic stability; nondifferentiable output signal function; stability conditions; strictly monotone increasing output signal function; two-layer heteroassociative networks; Artificial neural networks; Associative memory; Asymptotic stability; Bidirectional control; Correlators; Delay effects; Educational institutions; Magnesium compounds; Neural networks; Sufficient conditions;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on

Conference_Location

Hefei

Print_ISBN

0-7803-5995-X

Type

conf

DOI

10.1109/WCICA.2000.863341

Filename

863341