Approximation capabilities of multilayer feedforward regular fuzzy neural networks (Q5936230)

Four-layer feedforward regular fuzzy neural networks are constructed. Universal approximations to some continuous fuzzy functions defined on \({\mathcal F}_0(\mathbb{R})^n\) by the four-layer fuzzy neural networks are shown. At first, multivariate Bernstein polynomials associated with fuzzy valued functions are employed to approximate continuous fuzzy valued functions defined on each compact set of \(\mathbb{R}^n\). Secondly, by introducing cut-preserving fuzzy mapping, the equivalent conditions for continuous that can be arbitrarily closely approximated by regular fuzzy neural networks are shown. Finally a few of necessary and sufficient conditions for characterizing approximation capabilities of regular fuzzy neural networks are obtained. And some concrete fuzzy functions demonstrate our conclusions.