中国物理B ›› 2012, Vol. 21 ›› Issue (3): 38703-038703.doi: 10.1088/1674-1056/21/3/038703

• INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY • 上一篇    下一篇

王兴元,张诣   

  • 收稿日期:2011-05-06 修回日期:2011-11-08 出版日期:2012-02-15 发布日期:2012-02-15
  • 通讯作者: 张诣,zoey0313@sina.com E-mail:zoey0313@sina.com

Chaotic diagonal recurrent neural network

Wang Xing-Yuan(王兴元) and Zhang Yi(张诣)†   

  1. School of Electronic and Information Engineering, Dalian University of Technology, Dalian 116024, China
  • Received:2011-05-06 Revised:2011-11-08 Online:2012-02-15 Published:2012-02-15
  • Contact: Zhang Yi,zoey0313@sina.com E-mail:zoey0313@sina.com
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 61173183, 60973152, and 60573172), the Superior University Doctor Subject Special Scientific Research Foundation of China (Grant No. 20070141014), and the Natural Science Foundation of Liaoning Province, China (Grant No. 20082165).

PDF (PC)

690

赞

Abstract: We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.

Key words: diagonal recurrent neural network, chaos, cubic symmetry map

中图分类号:  (Neuronal network dynamics)

  • 87.19.lj
05.45.Gg (Control of chaos, applications of chaos)