Globally Exponential Stability of Delayed Neural Networks with Impulses

The present paper is mainly concerned with the issues of global exponential stability in recurrent delayed neural networks in the presence of impulsive connectivity between the neurons. By establishing an extended Halanay differential inequality on impulsive delayed neural networks, some simple yet generic criteria for global exponential stability of such neural networks are derived analytically. Compared with some existing works, the distinctive feature of these criteria is that it is not necessary to learn the priori information about the stability of the corresponding neural networks without impulses, which means the recurrent delayed neural networks can be globally exponentially stabilized by impulses even if the corresponding neural networks without impulses may be unstable or chaotic itself. Moreover, examples and simulations are given to illustrate the practical nature of the novel results.