Title :
Fuzzy neural nets can solve the overfitting problem
Author :
Feuring, Thomas ; Buckley, James J. ; Hayashi, Yoichi
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Siegen Univ., Germany
Abstract :
Given most continuous h:[a,b]→R and ε>0, we show how to obtain a neural net which will approximate h, to within ε, uniformly over [a,b]. To construct this neural net, we first train a fuzzy neural net on a finite training set, and the needed neural net is the defuzzified trained fuzzy neural net
Keywords :
curve fitting; fuzzy neural nets; fuzzy set theory; learning (artificial intelligence); finite training set; fuzzy neural net; fuzzy set theory; learning algorithm; overfitting problem; Computer science; Equations; Fuzzy neural networks; Fuzzy sets; Mathematics; Neural networks; Testing;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.830838
