標題: Dynamical optimal training for interval type-2 fuzzy neural network (T2FNN)
作者: Wang, CH
Cheng, CS
Lee, TT
電控工程研究所
Institute of Electrical and Control Engineering
關鍵字: interval type-2 FNN;dynamic optimal learning rate;back propagation
公開日期: 2003
摘要: Type-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.
URI: http://hdl.handle.net/11536/18534
ISBN: 0-7803-7952-7
ISSN: 1062-922X
期刊: 2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS
起始頁: 3663
結束頁: 3668
Appears in Collections:Conferences Paper