Title: | FEED-FORWARD NEURAL NETWORKS TRAINING: A COMPARISON BETWEEN GENETIC ALGORITHM AND BACK-PROPAGATION LEARNING ALGORITHM |
Authors: | Che, Zhen-Guo Chiang, Tzu-An Che, Zhen-Hua 資訊管理與財務金融系 註:原資管所+財金所 Department of Information Management and Finance |
Keywords: | Back-propagation neural network;Genetic algorithm;Feed-forward neural network |
Issue Date: | 1-Oct-2011 |
Abstract: | This study discusses the advantages and characteristics of the genetic algorithm and back-propagation neural network to train a feed-forward neural network to cope with weighting adjustment problems. We compare the performances of a back-propagation neural network and genetic algorithm in the training outcomes of three examples by referring to the measurement indicators and experiment data. The results show that the back-propagation neural network is superior to the genetic algorithm. Also, the back-propagation neural network has faster training speed than the genetic algorithm. However, the back-propagation neural network has the shortcoming of overtraining, while the genetic algorithm does not. The experiment result proves that the back-propagation neural network yields better outcomes than the genetic algorithm. |
URI: | http://hdl.handle.net/11536/14780 |
ISSN: | 1349-4198 |
Journal: | INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL |
Volume: | 7 |
Issue: | 10 |
Begin Page: | 5839 |
End Page: | 5850 |
Appears in Collections: | Articles |