Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms

Wenjian Wang; Weizhen Lu; Andrew Y.T. Leung; Siu-Ming Lo; Zongben Xu; Xiekang Wang

Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms

Wenjian Wang, Weizhen Lu, Andrew Y.T. Leung, Siu-Ming Lo, Zongben Xu, Xiekang Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

9 Citations (Scopus)

Abstract

The determination of the proper size of an artificial neural network (ANN) is recognized to be crucial, especially for its practical implementation in important issues such as learning and generalization. In this paper, an effective designing method of neural network architectures is presented. The network is firstly trained by a dynamic constructive method until the error is satisfied. The trained network is then pruned by genetic algorithm (GA). The simulation results demonstrate the advantages in generalization and expandability of the proposed method.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Pages	636-641
Volume	1
Publication status	Published - 2002
Externally published	Yes
Event	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States Duration: 12 May 2002 → 17 May 2002

Publication series

Name
Volume	1

Conference

Conference	2002 International Joint Conference on Neural Networks (IJCNN '02)
Country/Territory	United States
City	Honolulu, HI
Period	12/05/02 → 17/05/02

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{a357fed7beda4d9cac869f82913aa1db,

title = "Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms",

abstract = "The determination of the proper size of an artificial neural network (ANN) is recognized to be crucial, especially for its practical implementation in important issues such as learning and generalization. In this paper, an effective designing method of neural network architectures is presented. The network is firstly trained by a dynamic constructive method until the error is satisfied. The trained network is then pruned by genetic algorithm (GA). The simulation results demonstrate the advantages in generalization and expandability of the proposed method.",

author = "Wenjian Wang and Weizhen Lu and Leung, {Andrew Y.T.} and Siu-Ming Lo and Zongben Xu and Xiekang Wang",

year = "2002",

language = "English",

volume = "1",

pages = "636--641",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "2002 International Joint Conference on Neural Networks (IJCNN '02) ; Conference date: 12-05-2002 Through 17-05-2002",

}

Wang, W, Lu, W, Leung, AYT, Lo, S-M, Xu, Z & Wang, X 2002, Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms. in Proceedings of the International Joint Conference on Neural Networks. vol. 1, pp. 636-641, 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 12/05/02.

Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms. / Wang, Wenjian; Lu, Weizhen; Leung, Andrew Y.T. et al.
Proceedings of the International Joint Conference on Neural Networks. Vol. 1 2002. p. 636-641.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms

AU - Wang, Wenjian

AU - Lu, Weizhen

AU - Leung, Andrew Y.T.

AU - Lo, Siu-Ming

AU - Xu, Zongben

AU - Wang, Xiekang

PY - 2002

Y1 - 2002

N2 - The determination of the proper size of an artificial neural network (ANN) is recognized to be crucial, especially for its practical implementation in important issues such as learning and generalization. In this paper, an effective designing method of neural network architectures is presented. The network is firstly trained by a dynamic constructive method until the error is satisfied. The trained network is then pruned by genetic algorithm (GA). The simulation results demonstrate the advantages in generalization and expandability of the proposed method.

AB - The determination of the proper size of an artificial neural network (ANN) is recognized to be crucial, especially for its practical implementation in important issues such as learning and generalization. In this paper, an effective designing method of neural network architectures is presented. The network is firstly trained by a dynamic constructive method until the error is satisfied. The trained network is then pruned by genetic algorithm (GA). The simulation results demonstrate the advantages in generalization and expandability of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=0036079635&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0036079635&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

VL - 1

SP - 636

EP - 641

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - 2002 International Joint Conference on Neural Networks (IJCNN '02)

Y2 - 12 May 2002 through 17 May 2002

ER -

Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms

Abstract

Publication series

Conference

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this