Delay-dependent Robust Stability of Neutral-type Neural Networks with Time Delays*

In this paper, the problem of the global robust asymptotic stability (GRAS) for a class of interval neural networks described by nonlinear delayed differential equations of the neutral type is investigated. A series of sufficient criteria for such problems are obtained by employing Lyapunov-Krasovskii functional and LMI technique. These conditions are dependent on the size of the time delay, which are usually less conservative than delay-independent ones. Moreover, the activate functions in system are generalized without assuming the boundedness and differentiability. Finally, the effectiveness of the present results is demonstrated by numerical example.