Passivity and Passification of Memristor-Based Recurrent Neural Networks With Additive Time-Varying Delays.

This paper presents a new design scheme for the passivity and passification of a class of memristor-based recurrent neural networks (MRNNs) with additive time-varying delays. The predictable assumptions on the boundedness and Lipschitz continuity of activation functions are formulated. The systems considered here are based on a different time-delay model suggested recently, which includes additive time-varying delay components in the state. The connection between the time-varying delay and its upper bound is considered when estimating the upper bound of the derivative of Lyapunov functional. It is recognized that the passivity condition can be expressed in a linear matrix inequality (LMI) format and by using characteristic function method. For state feedback passification, it is verified that it is apathetic to use immediate or delayed state feedback. By constructing a Lyapunov-Krasovskii functional and employing Jensen's inequality and reciprocal convex combination technique together with a tighter estimation of the upper bound of the cross-product terms derived from the derivatives of the Lyapunov functional, less conventional delay-dependent passivity criteria are established in terms of LMIs. Moreover, second-order reciprocally convex approach is employed for deriving the upper bound for terms with inverses of squared convex parameters. The model based on the memristor with additive time-varying delays widens the application scope for the design of neural networks. Finally, pertinent examples are given to show the advantages of the derived passivity criteria and the significant improvement of the theoretical approaches.