Robust asymptotical stability for uncertain stochastic neural networks with discrete and distributed delays
Shuyun Wang, Shaoying Wang, Guogang Li, Zhifeng Gao · 2008
This paper investigates the problem of robust asymptotical stability for uncertain stochastic neural networks with discrete and distributed delays. Based on Lyapunov-Krasovskii functional and stochastic analysis method, new stability criteria is presented in terms of linear matrix inequalities to guarantee stochastic neural networks to be robustly asymptotically stable for all admissible parameter uncertainties, The criteria can be checked by utilizing the Matlab LMI toolbox. Two numerical examples are provided to demonstrate the feasibility of the proposed robust asymptotical stability criteria.