Title :
Adjusting fuzzy weights in fuzzy neural nets
Author :
Feuring, Thomas ; Buckley, James J. ; Hayashi, Yoichi
Author_Institution :
Inst. fur Inf., Munster Univ., Germany
Abstract :
In order to train fuzzy neural nets fuzzy number weights have to be adjusted. Because fuzzy arithmetic automatically leads to monotonic increasing outputs a direct fuzzification of the backpropagation method does not work. Therefore, the focus is on other strategies like evolutionary algorithms. In this paper we suggest a backpropagation based method of adjusting the weights. Furthermore we can show that for the proposed method convergence can be guaranteed
Keywords :
backpropagation; convergence; fuzzy neural nets; backpropagation based method; fuzzy arithmetic; fuzzy neural net training; fuzzy number weight adjustment; guaranteed convergence; monotonically increasing outputs; Arithmetic; Backpropagation algorithms; Computer science; Convergence; Error analysis; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Mathematics; Neural networks;
Conference_Titel :
Knowledge-Based Intelligent Electronic Systems, 1998. Proceedings KES '98. 1998 Second International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-4316-6
DOI :
10.1109/KES.1998.725940
