Fractional Voronovskaya type asymptotic expansions for quasi-interpolation neural network operators
Author
Anastassiou, George A.
Full text
https://revistas.ufro.cl/ojs/index.php/cubo/article/view/133210.4067/S0719-06462012000300005
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.