Novel stability criteria for recurrent neural networks with time-varying delay

This paper is concerned with the problem of stability analysis of recurrent neural networks with time-varying delay. An augmented Lyapunov–Krasovskii functional containing a triple integral term and considering more information of activation functions is constructed. Then, Wirtinger-based inequality and two zero-value free-weighting matrix equations are used to deal with the derivative of the Lyapunov–Krasovskii functional. Those treatments lead to less conservatism. A numerical example is given to verify the effectiveness and benefit of the proposed criteria.