时滞神经网络的指数稳定性分析

journal6 ›› 2008, Vol. 29 ›› Issue (4): 30-34.

时滞神经网络的指数稳定性分析

(重庆师范大学数学与计算机科学学院，重庆 400047)

出版日期:2008-07-25 发布日期:2012-05-21

Exponential Stability of Neural Networks with Time Delays

(Department of Mathematics and Computer Science,Chongqing Normal University,Chongqing 400047,China)

Online:2008-07-25 Published:2012-05-21
About author:YANG De-gang (1976-),male,was born in Zigong City,Sichuan Province,associate professor of Chongqing Normal University;research areas are neural networks,nonlinear dynamical systems and network security.
Supported by:
Supported by the NSFC (60573047);Natural Science Foundation Project of CQ CSTC (2006BB2254,2007BB2231);Applying Basic Research Program of Chongqing Education Committee (KJ060818);Doctoral Foundation Project of Chongqing Normal University (08XLB003)

摘要/Abstract

摘要：研究了一类时滞细胞神经网络的指数稳定性问题，利用Razumikhin定理和线性不等式技术得到新的全局指数稳定性准则.与其他方法不同之处在于，对神经网络模型的“线性化”，将神经网络模型变成一个线性时变的系统.所获的条件具有较少的保守性.最后用1个数值例子说明文中所得的结果是有效的.

关键词： 神经网络, 时滞, 指数稳定性, 线性矩阵不等式, Razumikhin定理

Abstract: This paper considers the problems of global exponential stability for a general class of neural networks with time delays,a new criterion ensuring global exponential stability is obtained by utilizing Razumikhin theorem and the linear matrix inequality (LMI) technique.Distinct difference from other analytical approaches lies in “linearization” of the neural network model,by which the considered neural network model is transformed into a linear time-variant system.The obtained conditions show to be less conservative and restrictive.A numerical simulation is given to illustrate the validity of our results.

Key words: neural networks, time delays, exponential stability, linear matrix inequality, Razumikhin theorem

杨德刚. 时滞神经网络的指数稳定性分析[J]. journal6, 2008, 29(4): 30-34.

YANG De-Gang. Exponential Stability of Neural Networks with Time Delays[J]. journal6, 2008, 29(4): 30-34.

参考文献

[1]CAO Jin-de.Periodic Oscillation and Exponential Stability of Delayed CNNs [J].Physics Letters A,2002,270(2-4):157-163.

[2]ARIK S.Stability Analysis of Delayed Neural Networks [J].IEEE Transactions on Circuits Systems I，2000,47(7):1 089-1 092.

[3]MOHAMAD S,GOPALSAMY K.Exponential Stability of Continuous-Time and Discrete-Time Cellular Neural Networks with Delays [J].Applied Mathematics and Computation，2003,135(1):17-38.

[4]LU Hong-tao,SHEN Rui-ming,CHUNG FU LAI.Global Exponential Convergence of Cohen-Grossberg Neural Networks with Time Delays [J].IEEE Transactions on Neural Networks,2005,16(6):1 694-1 696.

[5]LIAO Xiao-feng,CHEN Guan-rong,SANCHEZ E N.Delay-Dependent Exponential Stability Analysis of Delayed Neural Networks:An LMI Approach [J].Neural Networks，2002,15:855-866.

[6]LI Chuan-dong,LIAO Xiao-feng.Delay-Dependent Exponential Stability Analysis of Bi-Directional Associative Memory Neural Networks:An LMI Approach [J].Chaos,Solitons & Fractals,2005,24(4):1 119-1 134.

[7]LI Chuan-dong,LIAO Xiao-feng.New Algebraic Conditions for Global Exponential Stability of Delayed Recurrent Neural Networks [J].Neurocomputing,2005(64):319-333.

[8]QIAO Hong,PENG Ji-gen,XU Zong-ben.Nonlinear Measures:A New Approach toExponential Stability Analysis for Hopfield-Type Neural Networks [J].IEEE TNN,2001(12):360-370.

[9]LU Hong-tao,CHEN Guan-rong.Global Exponential Convergence of Multitime-Scale Neural Networks [J].IEEE Transactions on Circuits and Systems II:Express Briefs，2005,52(11):761-765.

[10]SANCHEZ E N,PEREZ J P.Input-to-State Stability Analysis for Dynamic NN [J].IEEE Transactions on Circuits Systems I，1999，46:1 895-1 398.

[11]BOYD S,GHAOUI L,FERON EI E，et al.Linear Matrix Inequalities in Systems and Control Theory [M].Philadephia:SIAM,1994.

[12]GU Ke-qin,CHEN Jie,KHARITONOV VLADIMIR L.Stability of Time-Delay System [M].New York：Springer-Verlag,2003.

[1]	叶海燕. 基于卷积神经网络的特定目标文本情感分析模型[J]. 吉首大学学报（自然科学版）, 2024, 45(1): 24-29.
[2]	郭红利, 谢景力, 张美杨. 受疾病意识影响的时滞传染病模型的动力学分析[J]. 吉首大学学报（自然科学版）, 2023, 44(5): 6-17.
[3]	张子振, 张伟诗. 具有阶段结构和同类相食的时滞捕食模型[J]. 吉首大学学报（自然科学版）, 2023, 44(4): 1-8.
[4]	张习盼, 沈长春. 中立型马尔可夫跳跃系统的可达集边界估计[J]. 吉首大学学报（自然科学版）, 2023, 44(2): 7-16.
[5]	彭春源, 沈长春. 广义半马尔可夫跳跃系统可达集边界估计[J]. 吉首大学学报（自然科学版）, 2023, 44(2): 17-23.
[6]	王宇, 张诗茹, 张渝佶, 周立群. 比例时滞神经网络的全局多项式镇定性[J]. 吉首大学学报（自然科学版）, 2022, 43(3): 15-25.
[7]	李家稳, 王崇旭, 王浩. 基于神经网络的桥下开挖竖向位移预测[J]. 吉首大学学报（自然科学版）, 2022, 43(2): 53-59.
[8]	张子振, 张伟诗. 一类考虑复吸的时滞戒烟模型[J]. 吉首大学学报（自然科学版）, 2022, 43(1): 1-9.
[9]	王雨嫣, 廖柏林, 彭晨, 李军, 印煜民. 递归神经网络研究综述[J]. 吉首大学学报（自然科学版）, 2021, 42(1): 41-48.
[10]	李钰，段明秀，宋思思，李翅. 基于深度学习SSD模型的人数统计技术[J]. 吉首大学学报（自然科学版）, 2020, 41(2): 19-22.
[11]	伍逸凡，朱龙娇，石俊萍. 人工神经网络在信息过滤中的应用[J]. 吉首大学学报（自然科学版）, 2019, 40(3): 17-22.
[12]	张永胜，肖林. 二次最小化问题的有限时间递归神经网络求解[J]. 吉首大学学报（自然科学版）, 2019, 40(2): 21-26.
[13]	贺电，谭渡渡，何海零，邹晟，钟佳辰，王庭婷. 基于气象大数据的配网故障数量预测[J]. 吉首大学学报（自然科学版）, 2019, 40(1): 53-56.
[14]	王军. 安徽省某地区中长期电力负荷预测[J]. 吉首大学学报（自然科学版）, 2018, 39(6): 46-49.
[15]	丁李，曾水玲，熊涛. 基于BP神经网络的湘西民间方块苗文特征提取方法[J]. 吉首大学学报（自然科学版）, 2018, 39(5): 14-18.