Fuzzy fractional more sigmoid function activated neural network approximations revisited

Here we study the univariate fuzzy fractional quantitative approximation of real valued functions on a compact interval by quasi-interpolation arctangent-algebraic-Gudermannian-generalized symmetrical activation function relied neural network operators. These approximations are derived establishing Jackson type inequalities involving moduli continuity right and left Caputo derivatives involved function. The pointwise uniform. related feed-forward networks with one hidden layer. We also integer derivative just continuous cases. Our result using higher order differentiation converges better than in case.