Applied Mathematics and Mechanics (English Edition) ›› 2001, Vol. 22 ›› Issue (3): 320-325.

• 论文 • 上一篇    下一篇

ESTIMATION OF ATTRACTION DOMAIN AND EXPONENTIAL CONVERGENCE RATE OF CONTINUOUS FEEDBACK ASSOCIATIVE MEMORY

周冬明1, 曹进德2, 李继彬3   

  1. 1. Department of Information and Electronic Science, Yunnan University, Kunming 650091, P. R. China;
    2. Adult Education College, Yunnan University, Kunming 650091, P. R. China;
    3. Center for Nonlinear Science Studies, Kunming University of Science and Technology, Kunming 650093, P. R. China
  • 收稿日期:1999-11-01 修回日期:2000-11-19 出版日期:2001-03-18 发布日期:2001-03-18
  • 基金资助:
    the Natural Science Foundation of Yunnan Province, China(1999F0017M)

ESTIMATION OF ATTRACTION DOMAIN AND EXPONENTIAL CONVERGENCE RATE OF CONTINUOUS FEEDBACK ASSOCIATIVE MEMORY

ZHOU Dong-ming1, CAO Jin-de2, LI Ji-bin3   

  1. 1. Department of Information and Electronic Science, Yunnan University, Kunming 650091, P. R. China;
    2. Adult Education College, Yunnan University, Kunming 650091, P. R. China;
    3. Center for Nonlinear Science Studies, Kunming University of Science and Technology, Kunming 650093, P. R. China
  • Received:1999-11-01 Revised:2000-11-19 Online:2001-03-18 Published:2001-03-18
  • Supported by:
    the Natural Science Foundation of Yunnan Province, China(1999F0017M)

摘要: The attraction domain of memory patterns and exponential convergence rate of the network trajectories to memory patterns for continuous feedback associative memory are estimated again by using of some analysis techniques and Liapunov method, some new results are obtained, that can be used for evaluation of fault-tolerance capability and the synthesis procedures for continuous feedback associative memory neural networks.

关键词: continuous feedback associative memory, Liapunov method, neural network, attraction domain, exponential convergence rate

Abstract: The attraction domain of memory patterns and exponential convergence rate of the network trajectories to memory patterns for continuous feedback associative memory are estimated again by using of some analysis techniques and Liapunov method, some new results are obtained, that can be used for evaluation of fault-tolerance capability and the synthesis procedures for continuous feedback associative memory neural networks.

Key words: continuous feedback associative memory, Liapunov method, neural network, attraction domain, exponential convergence rate

中图分类号: 

APS Journals | CSTAM Journals | AMS Journals | EMS Journals | ASME Journals