Improved delay-dependent stability results of recurrent neural networks

By using the fact that the activation functions are sector bounded and a tighter inequality, this paper presents a new method to the stability analysis of a class of recurrent neural networks (RNNs) with time-varying delays. This method includes more the slope of activation functions and less variables matrices in constructed Lyapunov-Krasovskii functional. With the present stability conditions, the computational burden and conservatism are largely reduced. Both theoretical analysis and numerical example are given to illustrate the effectiveness and the benefits of the proposed method.