应用科学学报 ›› 1999, Vol. 17 ›› Issue (3): 259-266.

• 论文 • 上一篇    下一篇

联想记忆混沌神经元网络

张毅锋, 杨绿溪, 何振亚   

  1. 东南大学
  • 收稿日期:1998-01-23 修回日期:1998-06-12 出版日期:1999-09-30 发布日期:1999-09-30
  • 基金资助:
    国家自然科学基金资助课题

Chaotic Neural Network for Associative Memory

ZHANG YIFENG, YANG LÜXI, HE ZHENYA   

  1. Department of Radio Engineering, Nanjing 210018
  • Received:1998-01-23 Revised:1998-06-12 Online:1999-09-30 Published:1999-09-30

摘要: 在对当前混沌神经元网络在信息处理中的应用研究的基础上,提出了对混沌神经元组成的人工神经网络模型建立一种新的自联想矩阵的方法,由此建立了由混沌神经元组成的改进的联想记忆网络.通过仿真实验证实了与现有方法相比,其联想的成功率和回忆速度方面都有较大的提高.并从理论上详细地分析了网络的联想记忆过程和性能提高的原因.

关键词: 联想记忆, 神经网络, 混沌映象

Abstract: Based on current research on applications of chaotic neurons network for information processing, a new auto-associative matrix is devised for artificial neural network composed of chaotic neurons. And then, a chaotic neurons network for associative memory is built up. From numerical simulation experiments, it has proved that its associative success rate and recall speed are improved by comparing with existing methods. Moveover, the associative recalling process of the network is theoretically analyzed in detail and explanations of improvement are given.

Key words: neural networks, chaotic map, associative memory