The study of fuzzy functions. I. Universal approximators
James J. Buckley, Thomas Feuring · 2002
We show how to construct a large class of universal approximators for fuzzy functions (which continuously map fuzzy numbers into fuzzy numbers and are the extension principle extensions of continuous real-valued functions). One important application is that layered, feedforward, neural nets, with real weights and bias terms and fuzzy signals, whose output is computed using the extension principle, are universal approximators for these functions.