Neural networks for optimal approximation of continuous functions in R^d

DOI10.1007/S11766-012-2789-8zbMATH Open1289.41024OpenAlexW2080366820MaRDI QIDQ377917FDOQ377917

Publication date: 19 November 2013

Published in: Applied Mathematics. Series B (English Edition) (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11766-012-2789-8

Recommendations

A note on neural networks for optimal approximation of continuous functions in \(\mathbb{R}^d\)
Neural networks with single hidden layer and the best polynomial approximation
Approximation properties of some two-layer feedforward neural networks
scientific article; zbMATH DE number 1977310
The ridge function representation of polynomials and an application to neural networks

zbMATH Keywords

neural network sigmoidal function ridge function approximation rate

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Approximation by other special function classes (41A30)

Cites Work

Approximation by superpositions of a sigmoidal function
Approximation by Ridge functions and neural networks with one hidden layer
Approximation by superposition of sigmoidal and radial basis functions
Title not available (Why is that?)
On relative real holomorphy rings
Generalization of Concepts Related to Linear Dependence
Interpolation in Several Variables
On Nonlinear Functions of Linear Combinations
Numerical Integration and Differentiation of Functions of Several Independent Variables by an Iterative Procedure

Cited In (40)

On PDE characterization of smooth hierarchical functions computed by neural networks
Continuous limits of residual neural networks in case of large input data
Perceptrons with polynomial post-processing
Hölder continuous activation functions in neural networks
Using neural network function approximation for optimal design of continuous-state parallel-series systems
Neural splines: exploiting parallelism for function approximation using modular neural networks
Networks of polynomial pieces with application to the analysis of point clouds and images
Approximation capabilities of neural networks
Title not available (Why is that?)
A class of universal approximators of real continuous functions revisited
On the antiderivatives of \(x^p/(1 - x)\) with an application to optimize loss functions for classification with neural networks
Feedforward neural networks and compositional functions with applications to dynamical systems
Continuity of approximation by neural networks in \(L_p\) spaces
Differentiable approximation by means of the Radon transformation and its applications to neural networks
Title not available (Why is that?)
Intelligent systems II. Complete approximation by neural network operators
Neural networks for optimal approximation of continuous functions on the unit sphere
Neural-network approximation of functions of several variables
On the tractability of multivariate integration and approximation by neural networks
Constructive approximation by Gaussian neural networks
Approximation properties of some two-layer feedforward neural networks
The capability of localized neural network approximation
Neural network approximation: three hidden layers are enough
Title not available (Why is that?)
Approximation by neural networks with a bounded number of nodes at each level
Continuous functions and neural network semantics
Title not available (Why is that?)
Some applications of artificial neural network in mathematics
Advances in Neural Networks – ISNN 2005
A note on neural networks for optimal approximation of continuous functions in \(\mathbb{R}^d\)
Neural network approximation
Two-hidden-layer feed-forward networks are universal approximators: a constructive approach
Compactness of neural networks
Construct theory of hierarchical functional networks and its application in multiple numerical integral
The ridge function representation of polynomials and an application to neural networks
Function approximation by deep neural networks with parameters \(\{0, \pm \frac{1}{2}, \pm 1,2\}\)
Simultaneous neural network approximation for smooth functions
Title not available (Why is that?)
Title not available (Why is that?)
Neural networks with single hidden layer and the best polynomial approximation

This page was built for publication: Neural networks for optimal approximation of continuous functions in \(\mathbb R^d\)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q377917)