完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Che, Zhen-Guo | en_US |
dc.contributor.author | Chiang, Tzu-An | en_US |
dc.contributor.author | Che, Zhen-Hua | en_US |
dc.date.accessioned | 2014-12-08T15:20:46Z | - |
dc.date.available | 2014-12-08T15:20:46Z | - |
dc.date.issued | 2011-10-01 | en_US |
dc.identifier.issn | 1349-4198 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/14780 | - |
dc.description.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. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | Back-propagation neural network | en_US |
dc.subject | Genetic algorithm | en_US |
dc.subject | Feed-forward neural network | en_US |
dc.title | FEED-FORWARD NEURAL NETWORKS TRAINING: A COMPARISON BETWEEN GENETIC ALGORITHM AND BACK-PROPAGATION LEARNING ALGORITHM | en_US |
dc.type | Article | en_US |
dc.identifier.journal | INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL | en_US |
dc.citation.volume | 7 | en_US |
dc.citation.issue | 10 | en_US |
dc.citation.spage | 5839 | en_US |
dc.citation.epage | 5850 | en_US |
dc.contributor.department | 資訊管理與財務金融系 註:原資管所+財金所 | zh_TW |
dc.contributor.department | Department of Information Management and Finance | en_US |
dc.identifier.wosnumber | WOS:000295904300016 | - |
dc.citation.woscount | 8 | - |
顯示於類別: | 期刊論文 |