| During the last decades,studying artificial neural networks has been the central focus of intensive research activities since these networks have found wide applications in areas like associativememory,pattern classification,reconstruction of moving images,signal processing,solving optimization problems.Different models of networks such as Hopfield neural networks,cellular neural networks,Cohen–Grossberg neural networks,and bidirectional associative memory neural networks have been extensively investigated in the literature.It's well known whether the system stable or not is very significant for the application.Since time delays are unavoidably encountered both in biological and in artificial neural systems,which may result in oscillation and instability,increasing attention has been focused on stability analysis of neural networks with time delays.In this paper,delay-dependent global asymptotic stability of switched Hopfield neural networks of neutral type was mainly studied.The main contents of this paper are as follows:Basing on the Lyapunov-Krasovskii stability theory,we build the new Lyapunov-krasovkii functions and use the quadratic convex combination method,the reciprocal convex combination approach,some generalized Jensen integral inequalities,and the free-weight matrix method in the process of proof to analysis the model of neural network in this paper.Our purpose is to present some new stability criteria which can help us verify the global asymptotic stability of switched Hopfield neural networks of neutral type.Finally,three numerical examples are given to demonstrate the effectiveness of our theoretical results over existing literature.The innovation points of this paper are as follows:1.The differentiability of the activation functions are not required and we can easily check the theoretical results and the sufficient conditions through the Matlab LMI Toolbox.2.We can demonstrate our theoretical results more effective and less conservative than the existing literature. |
PDF Full Text Request