Absolute exponential stability analysis of delayed neural networks

Abstract

In this Letter, we investigate the absolute exponential stability of a class of delayed neural networks. A new sufficient condition ensuring existence and uniqueness of equilibrium and its absolute exponential stability is derived. When the neural network model is simplified to one without delays, the present condition is reduced to the well-known additive diagonal stability condition of the interconnection weight matrix, which was previously established and proven to be general enough for ensuring stability of neural networks without delays in the literature. Thus, our condition generalizes the additive diagonal stability condition to the case of neural networks with delays.