Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, JM | en_US |
dc.contributor.author | Kao, CY | en_US |
dc.date.accessioned | 2014-12-08T15:44:25Z | - |
dc.date.available | 2014-12-08T15:44:25Z | - |
dc.date.issued | 2001 | en_US |
dc.identifier.issn | 0941-0643 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/29997 | - |
dc.description.abstract | A new evolutionary algorithm is introduced for training both feedforward and recurrent neural networks. The proposed approach, called the Family Competition Evolutionary Algorithm (FCEA), automatically achieves the balance of the solution quality and convergence speed by integrating multiple mutations, family competition and adaptive rides. We experimentally analyse the proposed approach by, showing that its components can cooperate with one another, and possess good local and global properties. Following the description of implementation details, our approach is then applied to several benchmark problems, including an artificial ant problem, parity problems and a two-spiral problem. Experimental results indicate that the new approach is able to stably solve these problems, and is very competitive with the comparative evolutionary algorithms. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | adaptive mutations | en_US |
dc.subject | evolutionary algorithm | en_US |
dc.subject | family competition | en_US |
dc.subject | multiple mutations | en_US |
dc.subject | neural networks | en_US |
dc.title | A robust evolutionary algorithm for training neural networks | en_US |
dc.type | Article | en_US |
dc.identifier.journal | NEURAL COMPUTING & APPLICATIONS | en_US |
dc.citation.volume | 10 | en_US |
dc.citation.issue | 3 | en_US |
dc.citation.spage | 214 | en_US |
dc.citation.epage | 230 | en_US |
dc.contributor.department | 生物科技學系 | zh_TW |
dc.contributor.department | Department of Biological Science and Technology | en_US |
dc.identifier.wosnumber | WOS:000173916700003 | - |
dc.citation.woscount | 20 | - |
Appears in Collections: | Articles |
Files in This Item:
If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.