Stability Analysis for a Class of Nonlinear Neural Networks with Multiple Delays

Author

Tang, Mei-Lan ; Liu, Xin-Ge

Author_Institution

Central South Univ., Changsha

fYear

2008

fDate

6-8 April 2008

Firstpage

1492

Lastpage

1495

Abstract

This paper investigates the global asymptotic stability (GAS) for a class of nonlinear neural networks with multiple delays. Based on Lyapunov stability theory, homeomorphism and the linear matrix inequality (LMI) technique, a new sufficient condition is proposed for (i) existence (ii) uniqueness and (iii) global asymptotic stability of equilibrium point, of a class of nonlinear neural networks without assuming that activation functions are bounded. An example is given to illustrate the effectiveness of our new stability criteria.

Keywords

Lyapunov methods; asymptotic stability; delays; linear matrix inequalities; neural nets; transfer functions; Lyapunov stability theory; activation functions; global asymptotic stability; homeomorphism; linear matrix inequality technique; multiple delays; nonlinear neural networks; stability analysis; sufficient condition; Asymptotic stability; Computers; Delay; Linear matrix inequalities; Lyapunov method; Neural networks; Neurons; Stability analysis; Stability criteria; Sufficient conditions;

fLanguage

English

Publisher

ieee

Conference_Titel

Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on

Conference_Location

Sanya

Print_ISBN

978-1-4244-1685-1

Electronic_ISBN

978-1-4244-1686-8

Type

conf

DOI

10.1109/ICNSC.2008.4525456

Filename

4525456