Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, CHen_US
dc.contributor.authorCheng, CSen_US
dc.contributor.authorLee, TTen_US
dc.date.accessioned2014-12-08T15:26:08Z-
dc.date.available2014-12-08T15:26:08Z-
dc.date.issued2003en_US
dc.identifier.isbn0-7803-7952-7en_US
dc.identifier.issn1062-922Xen_US
dc.identifier.urihttp://hdl.handle.net/11536/18534-
dc.description.abstractType-2 fuzzy logic system (FLS) cascaded with neural network called type-2 fuzzy neural network (T2FNN), is presented in this paper to handle uncertainty with dynamical optimal learning. A T2FNN consists of type-2 fuzzy linguistic process as the antecedent part and the two-layer interval neural network as the consequent part. The dynamical optimal training algorithm for the two-layer consequent part of interval T2FNN is first developed The stable and optimal left and right learning rates for the interval neural network, in the sense of maximum error reduction, can be derived for each iteration in the training process. It can also be shown both learning rates can not be both negative. Excellent results are obtained for the truck backing-up control, which yield more improved performance than those using type-1 FNN.en_US
dc.language.isoen_USen_US
dc.subjectinterval type-2 FNNen_US
dc.subjectdynamic optimal learning rateen_US
dc.subjectback propagationen_US
dc.titleDynamical optimal training for interval type-2 fuzzy neural network (T2FNN)en_US
dc.typeProceedings Paperen_US
dc.identifier.journal2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGSen_US
dc.citation.spage3663en_US
dc.citation.epage3668en_US
dc.contributor.department電控工程研究所zh_TW
dc.contributor.departmentInstitute of Electrical and Control Engineeringen_US
dc.identifier.wosnumberWOS:000186578600598-
Appears in Collections:Conferences Paper