New criteria of global exponential stability for a class of generalized neural networks with time-varying delays

In this paper, we essentially drop the requirement of Lipschitz condition on the activation functions. Only using physical parameters of neural networks, some new criteria concerning global exponential stability for a class of generalized neural networks with time-varying delays are obtained. The neural network model considered includes the delayed Hopfield neural networks, bidirectional associative memory networks, and delayed cellular neural networks as its special cases. Since these new criteria do not require the activation functions to be differentiable, bounded or monotone nondecreasing, the connection weight matrices to be symmetric and the delay function @t"i"j(t) to be differentiable, our results are mild and more general than previously known criteria. Four illustrative examples are given to demonstrate the effectiveness of the obtained results.