Exponential stability for switched neural networks with time-varying delays

This paper is concerned with the problem of exponential stability for a class of switched neural networks with time-varying delays. Based on the average dwell time (ADT) technique, mode-dependent average dwell time (MDADT) technique and multiple Lyapunov-Krasovskii (LK) function approach, two conditions are derived to design switching signal and guarantee the exponential stability of the considered neural networks, which are delay-dependent and formulated by linear matrix inequalities (LMIs). Finally, Numerical examples confirm the effectiveness and less conservativeness of the proposed methods.