New stability conditions for BAM neural networks with time delays

Author

Wu, Zhongfu ; Liao, Xiaofeng

Author_Institution

Fac. of Comput., Chongqing Univ., China

fYear

2000

fDate

2000

Firstpage

323

Lastpage

326

Abstract

In this paper, the Bi-directional Associative Memory (BAM) neural network with axonal signal transmission delay (DBAM) is considered. By combining a number of different Lyapunov functionals with the Razumikhin technique, some sufficient conditions for the existence of unique equilibrium and globally asymptotic stability are derived. These results are fairly general and can be verified easily. Besides, our approach for the analysis allows us to consider several different types of activation functions, including piecewise linear sigmoids with bounded activations as well as the usual C¹-smooth sigmoids. We believe that the results obtained have considerable significance in the design and application of the BAM neural network

Keywords

Lyapunov methods; asymptotic stability; content-addressable storage; delays; neural nets; piecewise linear techniques; stability criteria; BAM neural networks; C¹-smooth sigmoids; Lyapunov functionals; Razumikhin technique; activation functions; axonal signal transmission delay; bi-directional associative memory neural network; bounded activations; globally asymptotic stability; piecewise linear sigmoids; stability conditions; time delays; unique equilibrium; Artificial neural networks; Associative memory; Asymptotic stability; Computer networks; Delay effects; Lyapunov method; Magnesium compounds; Neural networks; Neurons; Sufficient conditions;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2000. IEEE APCCAS 2000. The 2000 IEEE Asia-Pacific Conference on

Conference_Location

Tianjin

Print_ISBN

0-7803-6253-5

Type

conf

DOI

10.1109/APCCAS.2000.913500

Filename

913500