Exponential Stabilization of Memristor-based Recurrent Neural Networks with Disturbance and Mixed Time Delays via Periodically Intermittent Control

A periodically intermittent control is considered for the memristor-based recurrent neural networks with disturbance and mixed time delays. The purpose of this study is to design the controller with less constraints, which is convenient for successful applications of memristor-based recurrent neural networks in complex environment. First, the estimate of the disturbance and mixed time delay are given by the assumptions. Then, by the method of Lyapunov-Krasovski functional, two new criteria ensuring globally exponential stabilization of the neural network are obtained under the controller, respectively. The proposed theoretical results indicate that the control width and control period are not constrained except that the control width has an upper bound. Furthermore, the design algorithm of controller is described. Finally, two examples are performed through four neural networks to illustrate the effectiveness of the proposed results.