DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeong, SY | ko |
dc.contributor.author | Lee, Soo-Young | ko |
dc.date.accessioned | 2009-09-03T05:37:18Z | - |
dc.date.available | 2009-09-03T05:37:18Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2000-11 | - |
dc.identifier.citation | NEUROCOMPUTING, v.35, pp.73 - 90 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | http://hdl.handle.net/10203/10966 | - |
dc.description.abstract | In this paper, adaptive learning algorithms to obtain better generalization performance are proposed. We specifically designed cost terms for the additional functionality based on the first- and second-order derivatives of neural activation at hidden layers. In the course of training, these additional cost functions penalize the input-to-output mapping sensitivity and high-frequency components in training data. A gradient-descent method results in hybrid learning rules to combine the error back-propagation, Hebbian rules, and the simple weight decay rules. However, additional computational requirements to the standard error back-propagation algorithm are almost negligible. Theoretical justifications and simulation results are given to verify the effectiveness of the proposed learning algorithms. (C) 2000 Elsevier Science B.V. All rights reserved. | - |
dc.description.sponsorship | This research was supported by Korean Ministry of Science and Technology as a Brain Science and Engineering Research Program (Braintech'21). | en |
dc.language | English | - |
dc.language.iso | en_US | en |
dc.publisher | ELSEVIER SCIENCE BV | - |
dc.subject | REGULARIZATION | - |
dc.title | Adaptive learning algorithms to incorporate additional functional constraints into neural networks | - |
dc.type | Article | - |
dc.identifier.wosid | 000165443200005 | - |
dc.identifier.scopusid | 2-s2.0-0034332435 | - |
dc.type.rims | ART | - |
dc.citation.volume | 35 | - |
dc.citation.beginningpage | 73 | - |
dc.citation.endingpage | 90 | - |
dc.citation.publicationname | NEUROCOMPUTING | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Lee, Soo-Young | - |
dc.contributor.nonIdAuthor | Jeong, SY | - |
dc.type.journalArticle | Article; Proceedings Paper | - |
dc.subject.keywordAuthor | adaptive learning algorithm | - |
dc.subject.keywordAuthor | mapping sensitivity | - |
dc.subject.keywordAuthor | curvature smoothing | - |
dc.subject.keywordAuthor | time-series prediction | - |
dc.subject.keywordPlus | REGULARIZATION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.