Global stability analysis in delayed Hopfield neural network models.

In this paper, without assuming the boundedness, monotonicity and differentiability of the activation functions, we present new conditions ensuring existence, uniqueness, and global asymptotical stability of the equilibrium point of Hopfield neural network models with fixed time delays or distributed time delays. The results are applicable to both symmetric and nonsymmetric interconnection matrices, and all continuous nonmonotonic neuron activation functions.