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

Author

Wang, Wenjian ; Lu, Weizhen ; Leung, Andrew Y T ; Lo, Siu-Ming ; Xu, Zongben ; Wang, Xichang

Author_Institution

Inst. for Inf. & Syst. Sci., Xi´´an Jiaotong Univ., China

Volume

1

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

636

Lastpage

641

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 the paper, an effective design 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

Keywords

feedforward neural nets; genetic algorithms; learning (artificial intelligence); neural nets; artificial neural network; dynamic constructive method; generalization; genetic algorithms; learning; neural network architectures; optimal feedforward neural networks; pruning; Algorithm design and analysis; Artificial neural networks; Computer architecture; Computer networks; Feedforward neural networks; Feedforward systems; Genetic algorithms; Neural networks; Neurons; Partial response channels;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1005546

Filename

1005546