Fuzzy fractional neural network approximation by Fuzzy Quasi-interpolation operators


Here we consider the univariate fuzzy fractional quantitative approximation of fuzzy real valued functions on a compact interval by quasi-interpolation sigmoidal and hyperbolic tangent fuzzy neural network operators. These approximations are derived by establishing fuzzy Jackson type inequalities involving the fuzzy moduli of continuity of the right and left Caputo fuzzy fractional derivatives of the engaged function. The approximations are fuzzy pointwise and fuzzy uniform. The related feed-forward fuzzy neural networks are with one hidden layer. Our fuzzy fractional approximation results into higher order converges better than the fuzzy ordinary ones.

Publication Title

Journal of Applied Nonlinear Dynamics