State estimation for neural networks with time-varying discrete and distributed delays

In this paper, the delay-dependent state estimation problem for a class of neural networks with time-varying discrete and distributed delays is concerned. The activation function is assumed to be neither monotonic nor differentiable, and a delay-dependent condition is established in terms of linear matrix inequality (LMI) to guarantee the dynamics of the estimation error is globally asymptotically stable. Finally, a numerical example with simulation results is provided to demonstrate the effectiveness of the proposed design method.