File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Adaptive learning rate for the training of B-spline networks

TitleAdaptive learning rate for the training of B-spline networks
Authors
Issue Date1998
Citation
Iee Conference Publication, 1998 n. 455, p. 342-347 How to Cite?
AbstractIn the training of B-spline networks, iterative gradient method with a constant learning rate are often used. It is well-known that the training speed depends on the choice of the learning rate, yet few guidelines in the selection of a suitable learning rate are available in the literature. In this paper, an adaptive learning rate to update the weights of a B-spline network with a scalar or multi-output is proposed. It is shown that under certain conditions, the performance index for a training algorithm using the proposed adaptive learning rate converges to a constant as the number of iterations increases. Also, a method for computing the criterion for terminating the training is presented. Simulation examples are presented, showing that training of the networks using the adaptive training is much faster than that using a constant learning rate.
Persistent Identifierhttp://hdl.handle.net/10722/158922
ISSN

 

DC FieldValueLanguage
dc.contributor.authorChan, CWen_HK
dc.contributor.authorJin, Hongen_HK
dc.contributor.authorCheung, KCen_HK
dc.contributor.authorZhang, HYen_HK
dc.date.accessioned2012-08-08T09:04:36Z-
dc.date.available2012-08-08T09:04:36Z-
dc.date.issued1998en_HK
dc.identifier.citationIee Conference Publication, 1998 n. 455, p. 342-347en_US
dc.identifier.issn0537-9989en_HK
dc.identifier.urihttp://hdl.handle.net/10722/158922-
dc.description.abstractIn the training of B-spline networks, iterative gradient method with a constant learning rate are often used. It is well-known that the training speed depends on the choice of the learning rate, yet few guidelines in the selection of a suitable learning rate are available in the literature. In this paper, an adaptive learning rate to update the weights of a B-spline network with a scalar or multi-output is proposed. It is shown that under certain conditions, the performance index for a training algorithm using the proposed adaptive learning rate converges to a constant as the number of iterations increases. Also, a method for computing the criterion for terminating the training is presented. Simulation examples are presented, showing that training of the networks using the adaptive training is much faster than that using a constant learning rate.en_HK
dc.languageengen_US
dc.relation.ispartofIEE Conference Publicationen_HK
dc.titleAdaptive learning rate for the training of B-spline networksen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailChan, CW: mechan@hkucc.hku.hken_HK
dc.identifier.emailCheung, KC: kccheung@hkucc.hku.hken_HK
dc.identifier.authorityChan, CW=rp00088en_HK
dc.identifier.authorityCheung, KC=rp01322en_HK
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.scopuseid_2-s2.0-0031638361en_HK
dc.identifier.issue455en_HK
dc.identifier.spage342en_HK
dc.identifier.epage347en_HK
dc.identifier.scopusauthoridChan, CW=7404814060en_HK
dc.identifier.scopusauthoridJin, Hong=34770583400en_HK
dc.identifier.scopusauthoridCheung, KC=7402406698en_HK
dc.identifier.scopusauthoridZhang, HY=7409196387en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats