Global asymptotic stability and global exponential stability of continuous-time recurrent neural networks

Author

Hu, Sanqing ; Wang, Jun

Author_Institution

Dept. of Autom. & Comput.-Aided Eng., Chinese Univ. of Hong Kong, Shatin, China

Volume

47

Issue

5

fYear

2002

fDate

5/1/2002 12:00:00 AM

Firstpage

802

Lastpage

807

Abstract

This paper presents new results on global asymptotic stability (GAS) and global exponential stability (GES) of a general class of continuous-time recurrent neural networks with Lipschitz continuous and monotone nondecreasing activation functions. We first give three sufficient conditions for the GAS of neural networks. These testable sufficient conditions differ from and improve upon existing ones. We then extend an existing GAS result to GES one and also extend the existing GES results to more general cases with less restrictive connection weight matrices and/or partially Lipschitz activation functions

Keywords

absolute stability; asymptotic stability; continuous time systems; recurrent neural nets; Lipschitz continuous activation functions; connection weight matrices; continuous-time recurrent neural networks; global asymptotic stability; global exponential stability; monotone nondecreasing activation functions; partially Lipschitz activation functions; sufficient conditions; testable sufficient conditions; Asymptotic stability; Automation; Councils; Linear matrix inequalities; Neural networks; Recurrent neural networks; Stability analysis; Sufficient conditions; Symmetric matrices; Testing;

fLanguage

English

Journal_Title

Automatic Control, IEEE Transactions on

Publisher

ieee

ISSN

0018-9286

Type

jour

DOI

10.1109/TAC.2002.1000277

Filename

1000277