Exponential Stability Analysis for Impulsive Neural Networks with Time-varying Delays

The main purpose of this paper is to further investigate the stability problem of impulsive neural networks with time-varying delays in the case that the underlying continuous delayed neural networks are unstable. By establishing an impulsive delayed differential inequality, some novel and less conservative criteria for global exponential stability of the equilibrium point of such model are derived analytically. It is shown that under certain conditions, impulses can make the underlying continuous unstable delayed neural networks globally exponentially stable. Our results have improved and generalized some published results and are help to design stability of neural networks when both delay effect and impulsive effect are taken into consideration. An example is also given to show the effectiveness of our results.