Stability Analysis Of Neural Networks With Impulses

Since neural network have a wide application on signal and image processing,artificial intelligence,many specialists and scholars apply themselves to the research of the theory and achieve many perfect products.In this dissertation,we study the asymptotic stability and exponential stability for neural networks with impulses. The main contents of this dissertation are as follows:Chapter1is introduction, it mainly involves the proposition of neural networks and the significance of stability analysis and introduces some related neural network model in this paper, the stability theory in dynamics and the main work in this paper.Chapter2uses the Lyapunov stability theory, the methods of M matrix and linear matrix inequality(LMI) and has studied Cohen-Grossberg Neural Networks(CGNN) model with time delays and impulses.Through construct the new M matrix,proposed global exponential stability conditions of neural networks. Examples are given to demonstrate the effectiveness of the proposed results in numerical examples by Matlab toolbox.Chapter3uses the Lyapunov stability theory, a kind of neural networks model with time delay in leakage term under impulsive perturbations.Through construct the new Lyapunov-Krasovskii function and apply the methods of linear matrix inequality(LMI),proposed global asymptomatic stability conditions of neural networks. Finally,demonstrate the effectiveness of the results in numerical examples by Matlab toolbox.