计算机科学 ›› 2010, Vol. 37 ›› Issue (12): 206-208.

• 人工智能 • 上一篇    下一篇

一种模糊Hopfield网络的学习算法及性质

曾水玲,杨静宇,徐蔚鸿   

  1. (吉首大学数学与计算机科学学院 吉首416000);(南京理工大学计算机科学与技术学院 南京210094);(长沙理工大学计算机和通信工程学院 长沙410077)
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金项目(No. 60632050),教育部重点科研项目(208098),湖南省教育厅科研基金重点项目(07A056)和湖南省教育厅科研基金优秀青年项目(10B088)资助。

Learning Algorithm and Properties on a Class of Fuzzy Hopfield Networks

ZENG Shui-ling,YANG Jing-yu,XU Wei hong   

  • Online:2018-12-01 Published:2018-12-01

摘要: 摘要现基于TL-模Max-TL模糊Hopfield网络(Max-TL FHNN)提出了一种有效的学习算法。对任意给定的模式集合,该学习算法总能找到使该模式集合成为Max-TL FHNN的平衡点集合的所有连接权矩阵中的最大者。任意给定的模式集合都能作为Max-TL FHNN网络的平衡点集合且能使Max-TL FHNN对任意输入在一步内就进入稳定状态,同时该网络对训练模式的摄动具有好的鲁棒性。

关键词: 模糊Hopfield网络,平衡点,学习算法,稳定性,鲁棒性

Abstract: In this paper, an efficient learning algorithm was proposed for a class of fuzzy Hopfield networks(Max-T FHNNs) based on I=norms. For any given set of patterns, the learning algorithm can find the maximum of all conneclion weight matrices that can make the set become a set of the equilibrium points of the Max-T FHNN when T is a left continuous T-norm. This maximal matrix is idempotent matrix in sense of Max-T composition, with which the Max-T FHNN can be convergent to a stable state in one iterative process for any input vector. It is proved theoretically that arbitrary set of patterns can become a set of the ectuilibrium points of every Max-T FHNN if only the T is left continuous T-norm. Max-TL FHNN has universally good robustness to perturbation of training pattern.

Key words: Hopfield network, Equilibrium point, Learning algorithm, Stability, Robustness

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!