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

被引:4
|
作者
Wang, WJ [1 ]
Lu, WZ [1 ]
Leung, AYT [1 ]
Lo, SM [1 ]
Xu, ZB [1 ]
Wang, XK [1 ]
机构
[1] Xian Jiaotong Univ, Fac Sci, Inst Informat, Xian 710049, Peoples R China
关键词
D O I
10.1109/IJCNN.2002.1005546
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:636 / 641
页数:2
相关论文
共 50 条