Neural nets can be universal approximators for fuzzy functions

We first argue that the extension principle is too computationly involved to be an efficient way for a computer to evaluate fuzzy functions. We then suggest using alpha-cuts and interval arithmetic to compute the values of fuzzy functions. Using this method of computing fuzzy functions, we then show that neural nets are universal approximators for (computable) fuzzy functions, when we only input non-negative, or non-positive, fuzzy numbers.