File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Learning From Neural Control

TitleLearning From Neural Control
Authors
Issue Date2003
Citation
Proceedings Of The Ieee Conference On Decision And Control, 2003, v. 6, p. 5721-5726 How to Cite?
AbstractOne of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, we firstly present an adaptive neural controller which is capable of learning the system dynamics during tracking control to periodic reference orbits. A partial persistent excitation (PE) condition is shown to be satisfied, and accurate NN approximation for the unknown dynamics is obtained in a local region along the tracking orbit. Secondly, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve local stability and better control performance. The significance of this paper is that it presents a dynamical deterministic learning theory, which can implement learning and control abilities similarly to biological systems.
Persistent Identifierhttp://hdl.handle.net/10722/169812
ISSN
2020 SCImago Journal Rankings: 0.395
References

 

DC FieldValueLanguage
dc.contributor.authorWang, Cen_US
dc.contributor.authorHill, DJen_US
dc.date.accessioned2012-10-25T04:55:48Z-
dc.date.available2012-10-25T04:55:48Z-
dc.date.issued2003en_US
dc.identifier.citationProceedings Of The Ieee Conference On Decision And Control, 2003, v. 6, p. 5721-5726en_US
dc.identifier.issn0191-2216en_US
dc.identifier.urihttp://hdl.handle.net/10722/169812-
dc.description.abstractOne of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, we firstly present an adaptive neural controller which is capable of learning the system dynamics during tracking control to periodic reference orbits. A partial persistent excitation (PE) condition is shown to be satisfied, and accurate NN approximation for the unknown dynamics is obtained in a local region along the tracking orbit. Secondly, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve local stability and better control performance. The significance of this paper is that it presents a dynamical deterministic learning theory, which can implement learning and control abilities similarly to biological systems.en_US
dc.languageengen_US
dc.relation.ispartofProceedings of the IEEE Conference on Decision and Controlen_US
dc.titleLearning From Neural Controlen_US
dc.typeConference_Paperen_US
dc.identifier.emailHill, DJ:en_US
dc.identifier.authorityHill, DJ=rp01669en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1109/CDC.2003.1271916en_US
dc.identifier.scopuseid_2-s2.0-1542378336en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-1542378336&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume6en_US
dc.identifier.spage5721en_US
dc.identifier.epage5726en_US
dc.identifier.scopusauthoridWang, C=35231325100en_US
dc.identifier.scopusauthoridHill, DJ=35398599500en_US
dc.identifier.issnl0191-2216-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats