DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Heung Bum | - |
dc.contributor.author | Jung, Sung Hoon | - |
dc.contributor.author | Kim, Tag Gon | - |
dc.contributor.author | Park, Kyu Ho | - |
dc.date.accessioned | 2011-09-09T01:01:45Z | - |
dc.date.available | 2011-09-09T01:01:45Z | - |
dc.date.issued | 1996-02-08 | - |
dc.identifier.citation | Neurocomputing, Vol.11, pp.101-106 | en |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | http://hdl.handle.net/10203/25146 | - |
dc.description.abstract | In training a back-propagation neural network, the learning speed of the network is greatly affected by its learning rate. None, however, has offered a deterministic method for selecting the optimal learning rate. Some researchers have tried to find the sub-optimal learning rates using various techniques at each training step. This paper proposes a new method for selecting the sub-optimal learning rates by an evolutionary adaptation of learning rates for each layer at every training step. Simulation results show that the learning speed achieved by our method is superior to that of other adaptive selection methods. | en |
dc.description.sponsorship | We would like to thank the three anonymous reviewers, whose insightful suggestions contributed to improve this article. | en |
dc.language.iso | en_US | en |
dc.publisher | Elsevier | en |
dc.subject | Back-propagation neural network | en |
dc.subject | Adaptive learning rates | en |
dc.subject | Evolutionary programming | en |
dc.title | Fast learning method for back-propagation neural network by evolutionary adaptation of learning rates | en |
dc.type | Article | en |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.