Univariate error function based neural network approximation

MaRDI QIDQ2944113zbMATH OpenFDO

Authors George A. Anastassiou

Publication date 7 September 2015

Full work available at URL https://arxiv.org/abs/1404.6449

zbMATH Keywords

Baskakov operatorCaputo fractional derivativecomplex approximationerror functionfractional approximationmodulus of continuityneural network approximationquadrature operatorquasi-interpolation operator

Mathematics Subject Classification ID

Fractional derivatives and integrals (26A33) Inequalities in approximation (Bernstein, Jackson, Nikol'ski?-type inequalities) (41A17) Rate of convergence, degree of approximation (41A25) Approximation by other special function classes (41A30) Approximation by positive operators (41A36)

Abstract: Here we research the univariate quantitative approximation of real and complex valued continuous functions on a compact interval or all the real line by quasi-interpolation, Baskakov type and quadrature type neural network operators. We perform also the related fractional approximation. These approximations are derived by establishing Jackson type inequalities involving the modulus of continuity of the engaged function or its high order derivative or fractional derivatives. Our operators are defined by using a density function induced by the error function. The approximations are pointwise and with respect to the uniform norm. The related feed-forward neural networks are with one hidden layer.

Recommendations

• Multivariate error function based neural network approximations
• Univariate sigmoidal neural newtwork approximation
• Voronovskaya type asymptotic expansions for error function based quasi-interpolation neural network operators
• Univariate hyperbolic tangent neural network approximation
• Fractional neural network approximation

Cited in

(7)

• Univariate sigmoidal neural newtwork approximation
• Multivariate error function based neural network approximations
• Fractional neural network approximation
• Quantitative approximation by a Kantorovich-Shilkret quasi-interpolation neural network operator
• Univariate hyperbolic tangent neural network approximation
• scientific article; zbMATH DE number 7686260 (Why is no real title available?)
• Quantitative approximation by multiple sigmoids Kantorovich-Shilkret quasi-interpolation neural network operators

This page was built for publication: Univariate error function based neural network approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2944113)