Algebraic function based Banach space valued ordinary and fractional neural network approximations

Here we research the univariate quantitative approximation, ordinary and fractional, of Banach space valued continuous functions on a compact interval or all real line by quasi-interpolation neural network operators. These approximations are derived establishing Jackson type inequalities involving modulus continuity engaged function its high order derivative fractional derivatives. Our operators defined using density generated an algebraic sigmoid function. The pointwise uniform norm. related feed-forward networks with one hidden layer.