Global exponential stability in a Lagrange sense for memristive recurrent neural networks with time-varying delays

In this paper, we consider the global exponential stability in a Lagrange sense for memristive recurrent neural networks with time-varying delays. Here, we adopt nonsmooth analysis and control theory to handle memristive neural networks with discontinuous right-hand side, and by constructing proper Lyapunov functionals and using inequality technique, several new sufficient conditions in linear matrix inequality form are given to ensure the ultimate boundedness and global exponential attractivity of the memristor-based neural networks in the sense of Filippov solutions. In addition, these conditions do not require the connection weight matrices to be symmetric and the delay functions to be differentiable. Finally, numerical simulations illustrate the effectiveness of our results.