Almost optimal estimates for approximation and learning by radial basis function networks

DOI10.1007/s10994-013-5406-zzbMath1320.68141OpenAlexW2110456244MaRDI QIDQ2251472

Yuanhua Rong, Xia Liu, Shao-Bo Lin, Zong Ben Xu

Publication date: 14 July 2014

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-013-5406-z

zbMATH Keywords

rate of convergenceradial basis function networksmachine learningempirical risk minimizationapproximation of differentiable multivariate functions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (8)

The Hermit-Type Reproducing Kernel Particle Method for Elasticity Problems ⋮ Radial basis reproducing kernel particle method for piezoelectric materials ⋮ Nonlinear approximation via compositions ⋮ Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation ⋮ Learning sparse and smooth functions by deep sigmoid nets ⋮ The numerical analysis of piezoelectric ceramics based on the Hermite-type RPIM ⋮ Deep Network Approximation Characterized by Number of Neurons ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The essential rate of approximation for radial function manifold
• On the tractability of multivariate integration and approximation by neural networks
• A bound on the approximation order of surface splines
• Lower bounds for approximation by MLP neural networks
• Entropy and the combinatorial dimension
• Improved multiquadric method for elliptic partial differential equations via PDE collocation on the boundary
• On lower bounds in radial basis approximation
• A distribution-free theory of nonparametric regression
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• On best approximation of classes by radial functions
• On quasi-interpolation by radial basis functions with scattered centres
• Error estimates and condition numbers for radial basis function interpolation
• Approximation by radial basis functions with finitely many centers
• The rate of approximation of Gaussian radial basis neural networks in continuous function space
• Essential rate for approximation by spherical neural networks
• Optimal rates for the regularized least-squares algorithm
• Approximation methods for supervised learning
• Approximation and learning by greedy algorithms
• Approximation in learning theory
• Approximation by neural networks and learning theory
• Approximation with polynomial kernels and SVM classifiers
• Pseudo-dimension and entropy of manifolds formed by affine-invariant dictionary
• On the mathematical foundations of learning
• Optimal rate of the regularized regression learning algorithm
• A radial basis function method for the shallow water equations on a sphere
• Universal approximation bounds for superpositions of a sigmoidal function
• Lower bounds for multivariate approximation by affine-invariant dictionaries
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
• Scattered Data Approximation
• Error bounds for approximation with neural networks

This page was built for publication: Almost optimal estimates for approximation and learning by radial basis function networks