Robust Exponential Stability of Uncertain Delayed Neural Networks With Stochastic Perturbation and Impulse Effects

Author

Tingwen Huang ; Chuandong Li ; Shukai Duan ; Starzyk, J.A.

Author_Institution

Texas A&M Univ. at Qatar, Doha, Qatar

Volume

23

Issue

6

fYear

2012

fDate

6/1/2012 12:00:00 AM

Firstpage

866

Lastpage

875

Abstract

This paper focuses on the hybrid effects of parameter uncertainty, stochastic perturbation, and impulses on global stability of delayed neural networks. By using the Ito formula, Lyapunov function, and Halanay inequality, we established several mean-square stability criteria from which we can estimate the feasible bounds of impulses, provided that parameter uncertainty and stochastic perturbations are well-constrained. Moreover, the present method can also be applied to general differential systems with stochastic perturbation and impulses.

Keywords

Lyapunov methods; asymptotic stability; delays; linear matrix inequalities; neural nets; perturbation techniques; stability criteria; stochastic processes; transient response; uncertain systems; Halanay inequality; Ito formula; Lyapunov function; general differential system; global stability; hybrid effect; impulse bound; impulse effect; linear matrix inequality; mean-square stability criteria; parameter uncertainty; robust exponential stability; stochastic perturbation; uncertain delayed neural network; Biological neural networks; Robustness; Stability criteria; Stochastic processes; Uncertain systems; Delayed neural networks (DNN); exponential stability; impulse; mean-square stability; parameter uncertainty; stochastic perturbation;

fLanguage

English

Journal_Title

Neural Networks and Learning Systems, IEEE Transactions on

Publisher

ieee

ISSN

2162-237X

Type

jour

DOI

10.1109/TNNLS.2012.2192135

Filename

6180003