A new global robust stability criteria for uncertain neural networks with fast time-varying delays

This paper deals with the problem of robust stability for uncertain neural networks with time-varying delays. The system possesses time-varying and norm-bounded uncertainties. The time-varying delay function in this paper is not required to be either continuously differentiable, or its derivative less than one. Based on Lyapunov-Krasovskii functional approach, new delay-dependent and delay-derivative-dependent stability criteria are presented, which are given in terms of linear matrix inequalities (LMIs). Numerical examples are given to illustrate the effectiveness and less conservativeness of the developed techniques.