Title :
Simulated annealing dynamic RPROP for training recurrent fuzzy systems
Author :
Mastorocostas, P.A. ; Rekanos, I.T.
Author_Institution :
Dept. of Informatics & Commun., Technol. Educ. Inst. of Serres
Abstract :
An adaptive learning method for recurrent fuzzy systems is proposed. The method modifies the SARPROP algorithm, originally developed for static neural models, in order to be applied to dynamic models. A comparative analysis with dynamic RPROP and back propagation through time is given, indicating the enhanced learning capabilities of the proposed algorithm
Keywords :
adaptive systems; backpropagation; fuzzy neural nets; fuzzy set theory; fuzzy systems; recurrent neural nets; simulated annealing; SARPROP algorithm; adaptive learning; back propagation; comparative analysis; dynamic RPROP; neural models; recurrent fuzzy system training; simulated annealing; Backpropagation algorithms; Communications technology; Convergence; Educational technology; Error correction; Fuzzy systems; Informatics; Learning systems; Neural networks; Simulated annealing;
Conference_Titel :
Fuzzy Systems, 2005. FUZZ '05. The 14th IEEE International Conference on
Conference_Location :
Reno, NV
Print_ISBN :
0-7803-9159-4
DOI :
10.1109/FUZZY.2005.1452546
