Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, Jingen_US
dc.contributor.authorChen, C. L. Philipen_US
dc.contributor.authorWang, Chi-Hsuen_US
dc.date.accessioned2018-08-21T05:56:33Z-
dc.date.available2018-08-21T05:56:33Z-
dc.date.issued2012-01-01en_US
dc.identifier.issn1062-922Xen_US
dc.identifier.urihttp://hdl.handle.net/11536/146339-
dc.description.abstractIn this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, conjugate gradients (CG) training algorithm is derived to tune both the premise and consequent part of FNN, and apparently increase the speed of convergence. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation achieves satisfactory results. Developing CG training algorithm for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing., etcen_US
dc.language.isoen_USen_US
dc.subjectNeural Networksen_US
dc.subjectFuzzy Logicen_US
dc.subjectFuzzy Neural Networksen_US
dc.subjectGradient Descenten_US
dc.subjectconjugate gradientsen_US
dc.titleOn the Conjugate Gradients (CG) Training Algorithm of Fuzzy Neural Networks (FNNs) via Its Equivalent Fully Connected Neural Networks (FFNNs)en_US
dc.typeProceedings Paperen_US
dc.identifier.journalPROCEEDINGS 2012 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC)en_US
dc.citation.spage2446en_US
dc.citation.epage2451en_US
dc.contributor.department電機工程學系zh_TW
dc.contributor.departmentDepartment of Electrical and Computer Engineeringen_US
dc.identifier.wosnumberWOS:000316869202097en_US
Appears in Collections:Conferences Paper