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

School of Mathematics and Statistics

Xi'an Jiaotong University

Research output: Contribution to conference › Paper › peer-review

10 Scopus citations

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
Pages	636-641
Number of pages	6
State	Published - 2002
Event	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States Duration: 12 May 2002 → 17 May 2002

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

Cite this

@conference{1cfa5652510a4d18a90ec9b2c840eee7,

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 Lo, \{Siu Ming\} and Zongben Xu and Xiekang Wang",

year = "2002",

language = "英语",

pages = "636--641",

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

}

TY - CONF

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 - https://www.scopus.com/pages/publications/0036079635

M3 - 论文

AN - SCOPUS:0036079635

SP - 636

EP - 641

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

Conference

Other files and links

Fingerprint

Cite this