文档介绍：
第 29 卷
第 4 期
吉首大学学报( 自然科学版) Vol. 29
No. 4
2008 年 7 月 ate the global exponential stability for a class of the neural network with time delays.
Firstly, we shifted the nonlinear neural network model to the linear one by employing a simple transformation. Then, we
establish sufficient conditions for the neural networks to be globally exponentially stable by utilizing Razumikhin Theo-
rem and using some wel-l know inequalities. Novel sufficient conditions lead to global exponential stability will be given.
An example is given to support our results.
The rest of this paper is organized as follows: In the following section, the problem to be studied is stated and some
needed preliminaries and lemmas are given. Based on the Razumikhin stability theorem, in combination with the LMI
technique, some stability conditions for DNNs are then derived in section 3. In section 4, an example is given to demon-
strate the effectiveness of our results. Finally, some conclusions are drawn in section 5.
2
Neural Network Model and Preliminaries
The delayed neural network model we consider is defined by the following state equations:
Received date: 2008- 02- 19
Foundation item: Supported by the NSFC ( 60573047 ) ; Natural Science Foundation Project of CQ CSTC ( 2006BB2254,
2007BB2231) ;