具有变时滞Hopfield神经网络的概周期解存在性与全局吸引性

数学物理学报 ›› 2004, Vol. 4 ›› Issue (6): 723-729.

具有变时滞Hopfield神经网络的概周期解存在性与全局吸引性

赵洪涌, 王广兰

新疆师范大学数学系乌鲁木齐 830054 南京大学数学系南京 210093

出版日期:2004-12-25 发布日期:2004-12-25
基金资助:
国家自然科学基金(10171044)、新疆师范大学校基金资助

Existence and Global Attractivity of Almost Periodic Solutions for Hopfield Neural |Networks |with Variable Delay

DIAO Hong-Yong, WANGGuang-Lan

Online:2004-12-25 Published:2004-12-25
Supported by:
国家自然科学基金(10171044)、新疆师范大学校基金资助

摘要/Abstract

摘要：

该文利用不动点理论和微分不等式分析等技巧，研究了变时滞Hopfield神经网络概周期解存在性及其全局吸引性, 所得准则改进了相关文献的结果。

关键词: Hopfield神经网络, 不动点理论;概周期解;全局吸引性, 一致有界

Abstract:

In the paper, using the theory of fixed point and differential inequality tec hnique, the authors study the existence and global attractivity of almost period ic solutio ns for Hopfield neural networks with variable delay. The criteria presented here are more general than those given in the related literature.

Key words: Hopfield neural networks; , Fixed point theory; , Almost Periodic solution, Global attractivity, Uniform boundedness.

中图分类号:

92B20

赵洪涌, 王广兰. 具有变时滞Hopfield神经网络的概周期解存在性与全局吸引性[J]. 数学物理学报, 2004, 4(6): 723-729.

DIAO Hong-Yong, WANGGuang-Lan. Existence and Global Attractivity of Almost Periodic Solutions for Hopfield Neural |Networks |with Variable Delay[J]. Acta mathematica scientia,Series A, 2004, 4(6): 723-729.

参考文献

[1]Hopfield J J.Neurons with graded response have collective computational prope rties like those of two stageneu rons.Proc Nat Acad Sci,1984,81: 3088-3092

[2]Kosko B. Neural Networks and Fuzzy Systems A Dynamical Systems App roach to Machine Intelligence. Engle wood Cliffs, NJ: Prentice Hall International Inc, 1992. 38-108

[3]Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proc Nat Acad USA,1982, 79: 2554-2558

[4]Hunt K J, Sbarbaro D, Zbikowki R. Neural networks for controlA survey. Automatic, 1992, 28: 1083-1112

[5]Zhao Hongyong, Xu Daoyi. Stability analysis of bidirectional associative memory neural networks with distributed delays.四川大学学报，2001, 38: 466-469

[6]Zhao Hongyong. Global stability of of bidirectional associative memory neural networks with distributed delays.Physics Letters A, 2002, 297: 182-190

[7]Xu Daoyi, Zhao HongyongInvariant and attracting sets of Hopfield neural networks with delays.International Journal of Systems Science, 2001, 32: 863-866

[8]Xu Daoyi, Zhao Hongyong. Global dynamics of Hopfield neural net works inv olving variable delays. Computers and Mathematics with Applications, 2001, 42: 39-45

[9]廖晓昕，肖冬梅. 具有变时滞的 Hopfield 型神经网络的全局指数稳定性. 电子学报2000, 28: 87-90

[10]曹进德，周冬明. 时延细胞神经网络的全局稳定性分析. 生物数学学报，1999, 14: 65-71

[11]廖晓峰，虞厥邦. 延迟双向联想记忆神经网络的周期振荡现象研究.电子科学学刊， 1999, 21: 60-65

[12]Cao Jinde. On exponential stability and periodic solutions of CNNS with delays. Physics Letters A, 2000, 267: 312-318

[13]Cao Jinde. Global exponential stability of Hopfield neural networks. International Journal of Systems Science, 2001, 32: 233-236

[14]廖六生. 二元神经网络的概周期解存在性. 生物数学学报，2001, 16: 169-174

[15]陈安平，黄立宏. Hopfield 神经网络的概周期解存在性和全局吸引性.数学物理学报，2001, 21A(4): 505-511

[16]Chen Anping, Cao Jinde. Almost periodic solution of shunting inhibitory CNNs with delays. 2002, 298: 161-170

[17]He Chongyou. Almost periodic differential equations.Beijing: Higher Education Publishing House, 1992 