This paper is concerned with the problem of stability for neural network with two time-varying delays, which has a wider range of applications than neural network with single time-varying delay. The system possesses two timevarying delays which are not required to be either continuously differentiable, or its derivative less than one. Based on Lyapunov-Krasovskii functional approach, Free-weight Matrix and Linear Matrix inequalities (LMIs), new delay-dependent and delay-derivative-dependent stability criteria are presented, and when one time-delay is fixed, the other maximum delay is better and even gets more than 6. An example is given to illustrate the effectiveness and less conservativeness of the developed techniques.

No abstract