The optimization to the structure of a continuous wavelet neural network

Xiao Dian Sun; Xue Mei Ren; Jie Chen; Cai Xia Tao

The optimization to the structure of a continuous wavelet neural network

Xiao Dian Sun^*, Xue Mei Ren, Jie Chen, Cai Xia Tao

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

Abstract

It is shown that the wavelet network structure with hidden layer decided by experience is not the optimization. In this paper we discuss the optimization to the structure of wavelet neural networks, for which the genetic algorithm is used to determine the number of elements in hidden layer while the gradient method of BP algorithm is used to compute weighting, stretching and displacing coefficients of the continuous wavelet neural networks. The effectiveness of the proposed scheme is demonstrated by examples.

Original language	English
Pages (from-to)	158-159
Number of pages	2
Journal	Xitong Fangzhen Xuebao / Journal of System Simulation
Volume	13
Issue number	SUPPL.
Publication status	Published - 2001

Keywords

Genetic algorithm
Gradient method
Optimization
Wavelet neural network

Cite this

@article{9067f5cc295c4d319933512d6c48e48e,

title = "The optimization to the structure of a continuous wavelet neural network",

abstract = "It is shown that the wavelet network structure with hidden layer decided by experience is not the optimization. In this paper we discuss the optimization to the structure of wavelet neural networks, for which the genetic algorithm is used to determine the number of elements in hidden layer while the gradient method of BP algorithm is used to compute weighting, stretching and displacing coefficients of the continuous wavelet neural networks. The effectiveness of the proposed scheme is demonstrated by examples.",

keywords = "Genetic algorithm, Gradient method, Optimization, Wavelet neural network",

author = "Sun, {Xiao Dian} and Ren, {Xue Mei} and Jie Chen and Tao, {Cai Xia}",

year = "2001",

language = "English",

volume = "13",

pages = "158--159",

journal = "Xitong Fangzhen Xuebao / Journal of System Simulation",

issn = "1004-731X",

publisher = "Acta Simulata Systematica Sinica",

number = "SUPPL.",

}

TY - JOUR

T1 - The optimization to the structure of a continuous wavelet neural network

AU - Sun, Xiao Dian

AU - Ren, Xue Mei

AU - Chen, Jie

AU - Tao, Cai Xia

PY - 2001

Y1 - 2001

N2 - It is shown that the wavelet network structure with hidden layer decided by experience is not the optimization. In this paper we discuss the optimization to the structure of wavelet neural networks, for which the genetic algorithm is used to determine the number of elements in hidden layer while the gradient method of BP algorithm is used to compute weighting, stretching and displacing coefficients of the continuous wavelet neural networks. The effectiveness of the proposed scheme is demonstrated by examples.

AB - It is shown that the wavelet network structure with hidden layer decided by experience is not the optimization. In this paper we discuss the optimization to the structure of wavelet neural networks, for which the genetic algorithm is used to determine the number of elements in hidden layer while the gradient method of BP algorithm is used to compute weighting, stretching and displacing coefficients of the continuous wavelet neural networks. The effectiveness of the proposed scheme is demonstrated by examples.

KW - Genetic algorithm

KW - Gradient method

KW - Optimization

KW - Wavelet neural network

UR - http://www.scopus.com/inward/record.url?scp=27644442068&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:27644442068

SN - 1004-731X

VL - 13

SP - 158

EP - 159

JO - Xitong Fangzhen Xuebao / Journal of System Simulation

JF - Xitong Fangzhen Xuebao / Journal of System Simulation

IS - SUPPL.

ER -

The optimization to the structure of a continuous wavelet neural network

Abstract

Keywords

Other files and links

Fingerprint

Cite this