Exponential stability of a class of generalized neural networks with time-varying delays

The dynamics of a class of generalized neural networks with time-varying delays are analyzed. Without constructing a Lyapunov function, general sufficient conditions for the existence, uniqueness and exponential stability of an equilibrium of the neural networks are obtained by the nonlinear Lipschitz measure approach. The new criteria are mild, independent of the delays and do not require the boundedness, differentiability or monotonicity assumption of the activation functions. Moreover, the proposed results extend and improve existing ones.