New delay-dependent stability criterion for discrete-time recurrent neural networks with time-varying delay

This paper studies the problem of stability analysis for discrete-time recurrent neural networks (DRNNs) with time-varying delays. Under a weak assumption on the activation functions, by defining a more general type of Lyapunov functionals and using a convex combination technique, a new delay-dependent stability criterion is proposed to guarantee the stability and uniqueness of equilibrium point of DRNNs in terms of linear matrix inequalities (LMIs). Compared with the existing results, the newly obtained stability condition is less conservative. A numerical example is given to illustrate the effectiveness and the benefits of the proposed method.