Fuzzy neural nets can solve the overfitting problem

Given most continuous h:[a,b]/spl rarr/R and /spl epsi/>0, we show how to obtain a neural net which will approximate h, to within /spl epsi/, 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.