Global Exponential Stability of Bidirectional Associative Memory Neural Networks With Time Delays

Author

Liu, Xin-Ge ; Martin, Ralph R. ; Wu, Min ; Tang, Mei-Lan

Author_Institution

Central South Univ., Changsha

Volume

19

Issue

3

fYear

2008

fDate

3/1/2008 12:00:00 AM

Firstpage

397

Lastpage

407

Abstract

In this paper, we consider delayed bidirectional associative memory (BAM) neural networks (NNs) with Lipschitz continuous activation functions. By applying Young´s inequality and Holder´s inequality techniques together with the properties of monotonic continuous functions, global exponential stability criteria are established for BAM NNs with time delays. This is done through the use of a new Lyapunov functional and an M-matrix. The results obtained in this paper extend and improve previous results.

Keywords

Lyapunov methods; asymptotic stability; content-addressable storage; delays; matrix algebra; stability criteria; transfer functions; Holder inequality techniques; Lipschitz continuous activation functions; Lyapunov functional; M-matrix; Young inequality techniques; bidirectional associative memory; delayed BAM neural networks; global exponential stability criteria; monotonic continuous functions; time delays; Bidirectional associative memory (BAM) neural networks (NNs); Lyapunov functionals; Young´s inequality; global exponential stability; Algorithms; Humans; Memory; Neural Networks (Computer); Nonlinear Dynamics; Time Factors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2007.908633

Filename

4392530