Chaotic diagonal recurrent neural network

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...

Full description

Saved in:
Bibliographic Details
Published inChinese physics B Vol. 21; no. 3; pp. 520 - 524
Main Authors Wang, Xing-Yuan, Zhang, Yi
Format Journal Article
LanguageEnglish
Published 01.03.2012
Subjects
Algorithms
Approximation
Chaos theory
Computer simulation
Learning
Mathematical analysis
Multilayers
Neural networks
Recurrent neural networks
仿真结果
多层前馈神经网络
学习算法
对角递归神经网络
混沌神经网络
逼近能力
Online AccessGet full text
ISSN1674-1056
2058-3834
1741-4199
DOI10.1088/1674-1056/21/3/038703

Cover

More Information
Summary: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.
Bibliography:diagonal recurrent neural network, chaos, cubic symmetry map
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.
Wang Xing-Yuan and Zhang Yi School of Electronic and Information Nngineering, DMian University of Technology, Dalian 116024, China
11-5639/O4
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1674-1056
2058-3834
1741-4199
DOI:10.1088/1674-1056/21/3/038703