Global Robust Asymptotical Stability of Generalized Recurrent Neural Networks with Mixed Time-Varying Delays

This paper is concerned with global robust asymptotical stability problem of a class of generalized recurrent neural networks with discrete and distributed time-varying delays. By employing a new Lyapunov-Krasovskii functional, aiming at the situation of the discrete and distributed time-varying delays without differentiability, a linear matrix inequality (LMI) approach is developed to establish a novel delay-dependent criterion for global robust asymptotical stability of the addressed neural networks. Additionally, the activation functions are assumed to be of more general descriptions. An example is given to show the proposed criterion is effective and less conservative than the previous ones.