Fractional Voronovskaya type asymptotic expansions for quasi-interpolation neural network operators

George A. Anastassiou

doi:10.4067/S0719-06462012000300005

Fractional Voronovskaya type asymptotic expansions for quasi-interpolation neural network operators

Authors

George A. Anastassiou Department of Mathematical Sciences, University of Memphis, Memphis, TN 38152, U.S.A.

DOI:

https://doi.org/10.4067/S0719-06462012000300005

Keywords:

Neural Network Fractional Approximation, Voro- novskaya Asymptotic Expansion, fractional derivative

Abstract

Here we study further the quasi-interpolation of sigmoidal and hyperbolic tangent types neural network operators of one hidden layer. Based on fractional calculus theory we derive fractional Voronovskaya type asymptotic expansions for the error of approximation of these operators to the unit operator.

Downloads

Download data is not yet available.

Downloads

Published

2012-10-01

How to Cite

[1]

G. A. Anastassiou, “Fractional Voronovskaya type asymptotic expansions for quasi-interpolation neural network operators”, CUBO, vol. 14, no. 3, pp. 71–83, Oct. 2012.