George A. Anastassiou
Voronovskaya type asymptotic expansions for smooth Symmetrized and Perturbed hyperbolic tangent ordinary and fractional neural network approximations over infinite domains
Neural, Parallel, and Scientific Computations 33 (2025) 1-24

https://doi.org/10.46719/NPSC2025.33.01

ABSTRACT.
In this article we research the univariate smooth approximation ordinary and fractional under differentiation of functions. The approximators here are neural network operators activated by the symmetrized and perturbed hyperbolic tangent function. All domains here are of the whole real line. The neural network operators here are of quasi-interpolation type: the basic ones, the Kantorovich type ones, and of the quadrature type. We give Voronovskaya type asymptotic expansions.

2020 Mathematics Subject Classification: 26A33, 41A17, 41A25, 41A30, 46B25.

Keywords and phrases: Symmetrized and Perturbed hyperbolic tangent function, quasi-interpolation neural network operators, ordinary and fractional approximation, Voronovskaya type asymptotic expansions.