A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves

DOI10.1016/j.jat.2006.12.009zbMath1119.41023OpenAlexW2011784318MaRDI QIDQ2643849

Andrew Vogt, Vera Kurková, Paul C. Kainen

Publication date: 27 August 2007

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jat.2006.12.009

zbMATH Keywords

Radon transformrates of approximationintegral formulasGaussian functioncharacteristic functions of closed half-spacesperceptron neural networksvariation with respect to half-spaces

Mathematics Subject Classification ID

Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (11)

Approximation of Sobolev classes by polynomials and ridge functions ⋮ Neural network with unbounded activation functions is universal approximator ⋮ Comparing fixed and variable-width Gaussian networks ⋮ Complexity estimates based on integral transforms induced by computational units ⋮ Can dictionary-based computational models outperform the best linear ones? ⋮ Minimization of Error Functionals over Perceptron Networks ⋮ Integral representations of shallow neural network with Rectified Power Unit activation function ⋮ Approximation rates for neural networks with general activation functions ⋮ Some comparisons of complexity in dictionary-based and linear computational models ⋮ Complexity of Shallow Networks Representing Finite Mappings ⋮ An Integral Upper Bound for Neural Network Approximation

Cites Work

• The Radon transform
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Uniform approximation by neural networks
• Approximation and learning of convex superpositions
• A better approximation for balls
• Geometry and topology of continuous best and near best approximations
• Integral combinations of Heavisides
• Real Interpolation of Sobolev Spaces on Subdomains of Rn
• Universal approximation bounds for superpositions of a sigmoidal function
• Dimension-independent bounds on the degree of approximation by neural networks
• Comparison of worst case errors in linear and neural network approximation
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves