Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation

DOI10.1007/s00009-021-01717-5zbMath1469.41006OpenAlexW3133433943MaRDI QIDQ2023320

Gianluca Vinti, Danilo Costarelli, Marco Cantarini

Publication date: 3 May 2021

Published in: Mediterranean Journal of Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00009-021-01717-5

zbMATH Keywords

asymptotic formula sigmoidal functions Voronovskaja formula neural networks operators high-order convergence truncated algebraic moment

Mathematics Subject Classification ID

Linear operator approximation theory (47A58) Interpolation in approximation theory (41A05) Rate of convergence, degree of approximation (41A25) Approximation by other special function classes (41A30)

Related Items (1)

Quantitative estimates for neural network operators implied by the asymptotic behaviour of the sigmoidal activation functions

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
The new forms of Voronovskaya's theorem in weighted spaces
Asymptotic formulae for linear combinations of generalized sampling operators
On the approximation by neural networks with bounded number of neurons in hidden layers
A unifying approach to convergence of linear sampling type operators in Orlicz spaces
Approximation properties for linear combinations of moment type operators
On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks
The approximation operators with sigmoidal functions
Uniform approximation by neural networks
Approximation by neural networks with a bounded number of nodes at each level
The universal approximation capabilities of cylindrical approximate identity neural networks
Saturation classes for MAX-product neural network operators activated by sigmoidal functions
Inverse results of approximation and the saturation order for the sampling Kantorovich series
Quantitative generalized Voronovskaja's formulae for Bernstein polynomials
Some inequalities in classical spaces with mixed norms
On the near optimality of the stochastic approximation of smooth functions by neural networks
Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions
On the approximation by single hidden layer feedforward neural networks with fixed weights
Optimal approximation of piecewise smooth functions using deep ReLU neural networks
An unsupervised parameter learning model for RVFL neural network
Convergence of a family of neural network operators of the Kantorovich type
Approximation by series of sigmoidal functions with applications to neural networks
The Bernstein Voronovskaja-type theorem for positive linear approximation operators
Approximate solutions of Volterra integral equations by an interpolation method based on ramp functions
Approximation of discontinuous signals by sampling Kantorovich series
Pointwise and uniform approximation by multivariate neural network operators of the max-product type
Detection of thermal bridges from thermographic images by means of image processing approximation algorithms
Learning theory estimates via integral operators and their approximations
Deep vs. shallow networks: An approximation theory perspective
Convergence for a family of neural network operators in Orlicz spaces
q-Voronovskaya type theorems forq-Baskakov operators
An Integral Upper Bound for Neural Network Approximation
Learning Theory
Another look at Voronovskaja type formulas
Convergence results for a family of Kantorovich max-product neural network operators in a multivariate setting
Approximation by truncated max‐product operators of Kantorovich‐type based on generalized (ϕ,ψ)‐kernels
On the Approximation of the Cut and Step Functions by Logistic and Gompertz Functions
Approximation by superpositions of a sigmoidal function

This page was built for publication: Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation