DocumentCode
303982
Title
FUNCOM: an efficient fuzzy neural training algorithm
Author
Mastorocostas, Paris ; Theocharis, John
Author_Institution
Dept. of Electr. & Comput. Eng., Aristotelian Univ. of Thessaloniki, Greece
Volume
1
fYear
1996
fDate
8-11 Sep 1996
Firstpage
380
Abstract
A novel algorithm for performing the parameter learning of fuzzy neural networks is suggested, based on the concept of constrained optimization. The algorithm is applied to off-line and online training problems and is compared to standard backpropagation and Fahlman´s Quickprop. The experimental results show the efficiency of the suggested algorithm and its superiority over the comparing rivals
Keywords
fuzzy logic; fuzzy neural nets; inference mechanisms; learning (artificial intelligence); optimisation; FUNCOM; Fahlman Quickprop; backpropagation; constrained optimization; fuzzy inference system; fuzzy logic; fuzzy neural networks; fuzzy neural training; off-line training; online training; parameter learning; Algorithm design and analysis; Computer networks; Constraint optimization; Electronic mail; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Inference algorithms; Input variables; Joining processes;
fLanguage
English
Publisher
ieee
Conference_Titel
Fuzzy Systems, 1996., Proceedings of the Fifth IEEE International Conference on
Conference_Location
New Orleans, LA
Print_ISBN
0-7803-3645-3
Type
conf
DOI
10.1109/FUZZY.1996.551771
Filename
551771
Link To Document