File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: B-spline recurrent neural network and its application to modelling of non-linear dynamic systems

TitleB-spline recurrent neural network and its application to modelling of non-linear dynamic systems
Authors
Chan, CWCheung, KCJin, HZhang, HY
KeywordsRecurrent Neural Network
B-Spline network
Adaptive Learning Algorithm
State Estimation
System Modelling
Issue Date1998
PublisherIEEE.
Citation
The 1998 American Control Conference, Philadelphia, PA., 24-26 June 1998. In Conference Proceedings, 1998, v. 1, p. 78-82 How to Cite?
DOI: http://dx.doi.org/10.1109/ACC.1998.694632
AbstractA new recurrent neural network based on B-spline function approximation is presented. The network can be easily trained and its training converges more quickly than that for other recurrent neural networks. Moreover, an adaptive weight updating algorithm for the recurrent network is proposed. It can speed up the training process of the network greatly and its learning speed is more quickly than existing algorithms, e.g., back-propagation algorithm. Examples are presented comparing the adaptive weight updating algorithm and the constant learning rate method, and illustrating its application to modelling of nonlinear dynamic system.
Persistent Identifierhttp://hdl.handle.net/10722/46636
ISBN
0-7803-4530-4

 

DC FieldValueLanguage
dc.contributor.authorChan, CWen_HK
dc.contributor.authorCheung, KCen_HK
dc.contributor.authorJin, Hen_HK
dc.contributor.authorZhang, HYen_HK
dc.date.accessioned2007-10-30T06:54:46Z-
dc.date.available2007-10-30T06:54:46Z-
dc.date.issued1998en_HK
dc.identifier.citationThe 1998 American Control Conference, Philadelphia, PA., 24-26 June 1998. In Conference Proceedings, 1998, v. 1, p. 78-82en_HK
dc.identifier.isbn0-7803-4530-4en_HK
dc.identifier.urihttp://hdl.handle.net/10722/46636-
dc.description.abstractA new recurrent neural network based on B-spline function approximation is presented. The network can be easily trained and its training converges more quickly than that for other recurrent neural networks. Moreover, an adaptive weight updating algorithm for the recurrent network is proposed. It can speed up the training process of the network greatly and its learning speed is more quickly than existing algorithms, e.g., back-propagation algorithm. Examples are presented comparing the adaptive weight updating algorithm and the constant learning rate method, and illustrating its application to modelling of nonlinear dynamic system.en_HK
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.relation.ispartofAmerican Control Conference Proceedings-
dc.rights©1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.subjectRecurrent Neural Networken_HK
dc.subjectB-Spline networken_HK
dc.subjectAdaptive Learning Algorithmen_HK
dc.subjectState Estimationen_HK
dc.subjectSystem Modellingen_HK
dc.titleB-spline recurrent neural network and its application to modelling of non-linear dynamic systemsen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0-7803-4530-4&volume=1&spage=78&epage=82&date=1998&atitle=B-spline+recurrent+neural+network+and+its+application+to+modelling+of+non-linear+dynamic+systemsen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ACC.1998.694632en_HK
dc.identifier.scopuseid_2-s2.0-47949083073-
dc.identifier.hkuros31907-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats