首页 | 本学科首页   官方微博 | 高级检索  
     

基于LMI的中立型Hopfield神经网络的稳定性
引用本文:佘秋野,陈丽换,张玉民,郭雷. 基于LMI的中立型Hopfield神经网络的稳定性[J]. 东南大学学报(自然科学版), 2005, 0(Z2)
作者姓名:佘秋野  陈丽换  张玉民  郭雷
作者单位:东南大学自动化研究所 南京210096(佘秋野,张玉民,郭雷),金陵科技学院机电工程学院 南京210001(陈丽换)
基金项目:国家自然科学基金资助项目(60474050),中国博士后基金资助项目(20040350655),江苏省博士后科研资助计划资助项目
摘    要:为了更加深入地了解神经网络的复杂性,研究了中立型Hopfield神经网络模型,对该模型的稳定性的判定进行了探讨.通过构造合适的Lyapunov泛函,借助线性矩阵不等式(LMI)的一些技巧以及Lyapunov-Krasovskii稳定性理论,给出了该神经网络模型稳定的充分条件,以及模型稳定时中立项所必须满足的必要条件.给出的结果改进了已有的结论和方法,在一定程度上降低了求解的难度,在实际应用方面更加简捷方便.仿真实例表明了算法的有效性,以及所存在的保守性.

关 键 词:中立系统  神经网络  稳定性  线性矩阵不等式

LMI-based stability analysis of neutral Hopfield neural networks
She Qiuye Chen Lihuan Zhang Yumin Guo Lei. LMI-based stability analysis of neutral Hopfield neural networks[J]. Journal of Southeast University(Natural Science Edition), 2005, 0(Z2)
Authors:She Qiuye Chen Lihuan Zhang Yumin Guo Lei
Affiliation:She Qiuye~1 Chen Lihuan~2 Zhang Yumin~1 Guo Lei~1
Abstract:To understand the complexity of neural networks more thoroughly,the neutral Hopfield neural networks model is researched.A discussion for the judgement of its stability is proceeded.By constructing proper Lyapunov functional,a sufficient condition and a necessary condition which the neutral item must satisfy when the model is steady are given based on LMI technique and Lyapunov-Krasovskii stability theory.The given result has improved the conclusion and the method existed.It has lowered the difficulty of solution in certain degree and is more convenient in application as well.The simulation shows the efficiency and the conservative of the presented algorithm.
Keywords:neutral system  neural networks  stability  linear matrix inequalities
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号