Delay-dependent stability for static recurrent neural networks via a piecewise delay approach

This paper studies the problem of asymptotic stability for static recurrent neural networks with time delay. Based on the piecewise delay approach, a new Lyapunov functional is constructed. The activation functions are assumed to be neither monotonic, nor differentiable, nor bounded. Without introducing any free-weighting matrices, some delay-range-dependent stability criteria are established. As a result, the criteria involve less variables and have low computational complexity. An example is given to show the effectiveness and the benefits of the proposed method.