时滞双向联想记忆神经网络的指数稳定性：联合周期间歇反馈脉冲控制.docVIP

  时滞双向联想记忆神经网络的指数稳定性： 联合周期间歇反馈脉冲控制 胡建强，梁金玲 东南大学数学系，南京 210096 摘要：本文研究了一类在联合周期间歇反馈脉冲控制策略下的带有离散时滞的双向联想记忆神 经网络的指数稳定性问题。与此同时，系统中的李普希兹激活函数不再要求是有界、单调以及 可微的。通过使用分析技巧和李亚普诺夫函数得到了系统全局指数稳定的充分判据。最后，数 值例子验证了理论结果的有效性。 关键词：双向联想记忆神经网络; 周期间歇控制；脉冲控制 中图分类号： O231.2 Exponential stability of BAM neural networks with delays via joint periodically intermittent and impulsive control HU Jian-Qiang, LIANG Jin-Ling Department of Mathematics, Southeast University, Nanjing 210096 Abstract: The exponetial stabilization problem for a class of bidirectional associative memory (BAM) neural networks with discrete delays by the joint periodically intermittent control and impulsive control scheme is investigated, meanwhile the Lipschitzian activation functions in the system do not have to assume their boundedness, monotonicity or di?erentiability. Some su?cient criteria for global exponential stability are derived by using analysis techniques and Lyapunov function. Finally, a illustrative example is given at the end of this paper to show the e?ectiveness of our results. Key words: Bidirectional associative memory neural networks; Periodically intermittent control; Impulsive control. 基金项目： The Specialized Research Fund for the Doctoral Program of Higher Education for New Teachers in China (200802861044) 作者简介： Hu Jianqiang (1988-), male, master student, major research direction: complex systems and network science. Correspondence author：Liang Jinling (1974-), female, associate professor, major research direction：complex networks, delay systems, robust control. -1-   0 Introduction Since the bidirectional associative memoey (BAM) neural networks known as an extension of unidirectional autoassociator of Hop?eld neural networks were ?rst proposed by Kosko, it has been widely studied due to its extensive applications such as pattern recognition, signal or image processing, solving optimization problems and automatic control. Later, Gopalsamy and He [1] studied a modi?cation of the origin model called bid