Reliable stabilization for memristor-based recurrent neural networks with time-varying delays

In this paper, a general class of memristive recurrent neural networks with time-varying delays is considered. Based on the knowledge of memristor and recurrent neural networks (RNNs), a model of memristive based RNNs is established. After that the problem of reliable stabilization is studied by constructing a suitable Lyapunov–Krasovskii functional (LKF) and using linear matrix inequality (LMI) framework. By use of the Wirtinger-type inequality, sufficient conditions are presented for the existence of a reliable state feedback controller, which can guarantee the global asymptotic stability of the memristive RNNs. Finally, an example is given to illustrate the theoretical results via numerical simulations.