File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Sequential RBF function estimator: memory regression network

TitleSequential RBF function estimator: memory regression network
Authors
Issue Date2004
PublisherInstitute of Electrical and Electronics Engineers. The Journal's website is located at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=9622
Citation
The 2004 IEEE International Conference on Systems, Man and Cybernetics (SMC 2004), Hague, The Netherlands, 10-13 October 2004. In IEEE International Conference on Systems, Man, and Cybernetics. Conference Proceedings, 2004, v. 5, p. 4815-4820 How to Cite?
AbstractThe newal-network training algorithm can be divided into 2 categories: (I) Batch mode and (2) Sequential mode. In this paper, a novel online RBF network called "Memory Regression Network (MRN)" is proposed. Different from the previous approaches [2, 11], MRN involves two types of memories: Experience and Neuron, which handle short and long term memories respectively. By simulating human's learning behavior, a given function can be estimated without memorizing the whole training set. Two sets of function estimation experiments are examined in order to illustrate the performance of the proposed algorithm. The results show that MRN can effectively approximate the given function within a reasonable time and acceptable mean square error. © 2004 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/196655
ISBN
ISSN

 

DC FieldValueLanguage
dc.contributor.authorChow, C-K-
dc.contributor.authorTsui, H-T-
dc.date.accessioned2014-04-24T02:10:31Z-
dc.date.available2014-04-24T02:10:31Z-
dc.date.issued2004-
dc.identifier.citationThe 2004 IEEE International Conference on Systems, Man and Cybernetics (SMC 2004), Hague, The Netherlands, 10-13 October 2004. In IEEE International Conference on Systems, Man, and Cybernetics. Conference Proceedings, 2004, v. 5, p. 4815-4820-
dc.identifier.isbn0-7803-8566-7-
dc.identifier.issn1062-922X-
dc.identifier.urihttp://hdl.handle.net/10722/196655-
dc.description.abstractThe newal-network training algorithm can be divided into 2 categories: (I) Batch mode and (2) Sequential mode. In this paper, a novel online RBF network called "Memory Regression Network (MRN)" is proposed. Different from the previous approaches [2, 11], MRN involves two types of memories: Experience and Neuron, which handle short and long term memories respectively. By simulating human's learning behavior, a given function can be estimated without memorizing the whole training set. Two sets of function estimation experiments are examined in order to illustrate the performance of the proposed algorithm. The results show that MRN can effectively approximate the given function within a reasonable time and acceptable mean square error. © 2004 IEEE.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's website is located at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=9622-
dc.relation.ispartofIEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rightsIEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings. Copyright © Institute of Electrical and Electronics Engineers.-
dc.titleSequential RBF function estimator: memory regression network-
dc.typeConference_Paper-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ICSMC.2004.1401293-
dc.identifier.scopuseid_2-s2.0-15744385926-
dc.identifier.volume5-
dc.identifier.spage4815-
dc.identifier.epage4820-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 160603 amended-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats