DocumentCode :
2910734
Title :
An automatic adjustment method of backpropagation learning parameters, using fuzzy inference
Author :
Ueno, Fumio ; Inoue, Takahiro ; Baloch, Badur-ul-Haque ; Yamamoto, Takayoshi
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Kumamoto Univ., Japan
fYear :
1992
fDate :
27-29 May 1992
Firstpage :
410
Lastpage :
414
Abstract :
Fuzzy inference is introduced into a conventional backpropagation learning algorithm for neural networks. This procedure repeatedly adjusts the learning parameters and leads the system to convergence at the earliest possible time. The technique is appropriate in the sense that optimum learning parameters are being applied in every learning cycle automatically, whereas conventional backpropagation does not contain any well-defined rule regarding the proper selection of learning parameters
Keywords :
backpropagation; fuzzy logic; inference mechanisms; neural nets; automatic adjustment; backpropagation; fuzzy inference; learning parameters; neural networks; Backpropagation algorithms; Computer errors; Computer science; Computer simulation; Inference algorithms; Mathematics; Multi-layer neural network; Neural networks; Neurons; Temperature;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multiple-Valued Logic, 1992. Proceedings., Twenty-Second International Symposium on
Conference_Location :
Sendai
Print_ISBN :
0-8186-2680-1
Type :
conf
DOI :
10.1109/ISMVL.1992.186824
Filename :
186824
Link To Document :
بازگشت