Global stability analysis of bidirectional associative memory neural networks with time delay

摘要

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 bidirectional associative memory neural networks with fixed time delays or distributed time delays. The results are applicable to both symmetric and non-symmetric interconnection matrices, and al continuous non-monotonic neuron activation functions.