Full Text:   <2548>

CLC number: TP18

On-line Access: 2024-08-27

Received: 2023-10-17

Revision Accepted: 2024-05-08

Crosschecked: 0000-00-00

Cited: 0

Clicked: 5159

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
1. Reference List
Open peer comments

Journal of Zhejiang University SCIENCE A 2000 Vol.1 No.3 P.322-326

http://doi.org/10.1631/jzus.2000.0322


AN IMPROVED GENETIC ALGORITHM FOR TRAINING LAYERED FEEDFORWARD NEURAL NETWORKS


Author(s):  LIU Ping, CHENG Yi-yu

Affiliation(s):  Dept.of Chemical Engineering, Zhejiang University, Hangzhou, 310027, China

Corresponding email(s): 

Key Words:  artificial neural network, genetic algorithms, layered feedforward neural networks


Share this article to: More

LIU Ping, CHENG Yi-yu. AN IMPROVED GENETIC ALGORITHM FOR TRAINING LAYERED FEEDFORWARD NEURAL NETWORKS[J]. Journal of Zhejiang University Science A, 2000, 1(3): 322-326.

@article{title="AN IMPROVED GENETIC ALGORITHM FOR TRAINING LAYERED FEEDFORWARD NEURAL NETWORKS",
author="LIU Ping, CHENG Yi-yu",
journal="Journal of Zhejiang University Science A",
volume="1",
number="3",
pages="322-326",
year="2000",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.2000.0322"
}

%0 Journal Article
%T AN IMPROVED GENETIC ALGORITHM FOR TRAINING LAYERED FEEDFORWARD NEURAL NETWORKS
%A LIU Ping
%A CHENG Yi-yu
%J Journal of Zhejiang University SCIENCE A
%V 1
%N 3
%P 322-326
%@ 1869-1951
%D 2000
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.2000.0322

TY - JOUR
T1 - AN IMPROVED GENETIC ALGORITHM FOR TRAINING LAYERED FEEDFORWARD NEURAL NETWORKS
A1 - LIU Ping
A1 - CHENG Yi-yu
J0 - Journal of Zhejiang University Science A
VL - 1
IS - 3
SP - 322
EP - 326
%@ 1869-1951
Y1 - 2000
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.2000.0322


Abstract: 
The new genetic algorithm for training layered feedforward neural networks proposed here uses a mutation operator for performing the search behaviors of local optimization. Combining the random restart method with the local search technique, the algorithm can converge asymptotically to the optimal solution. Test with a practical example showed that the improved genetic algorithm is more efficient than the conventional genetic algorithm.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Buford, D. S., Rakesh, S, 1986. Thermodynamic Data for Pure Compounds. Elsevier, Amsterdam.

[2]Chen, G. L., Wang, X. F. et al, 1996. Genetic algorithm and its application. People's Post Press, Beijing (in Chinese).

[3]Kitano, H., 1990. Empirical studies on the speed of convergence of neural network training using genetic algorithms, In: Proceedings AAAI-90, p. 789-795.

[4]Montana, D. J., Davis, L., 1989. Training feedforward neural networks using genetic algorithms. In: Proceedings IJCAI-89, p. 762-767.

[5]Vargaftik, N. B., 1975. Tables on the Thermophysical Properties of Liquids and Gases. Hemisphere Publishing Corporation, Wiley, New York, p.99-175.

[6]Xu, Z. B., Gao, Y., 1996. The characteristic analysis and prevention of premature convergence of genetic algorithms. Science in China, Ser. E, 26(4): 364-375.

[7]Byungjoo, Yoon, Holmes, Dawn J., et al., 1994. Efficient genetic algorithms for training layered feedforward neural networks. Information Sciences, 76: 67-85.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE