Hyperbolic Tangent Like Relied Banach Space Valued Neural Network Multivariate Approximations

Abstract

Abstract Here we examine the multivariate quantitative approximations of Banach space valued continuous multivariate functions on a box or ℝ N , N ∈ ℕ, by the multivariate normalized, quasi-interpolation, Kantorovich type and quadrature type neural network operators. We treat also the case of approximation by iterated operators of the last four types. These approximations are derived by establishing multidimensional Jackson type inequalities involving the multivariate modulus of continuity of the engaged function or its high order Fréchet derivatives. Our multivariate operators are defined by using a multidimensional density function induced by a hyperbolic tangent like sigmoid function. The approximations are pointwise and uniform. The related feed-forward neural network is with one hidden layer.