Linear and nonlinear approximation of spherical radial basis function networks

DOI10.1016/j.jco.2016.02.003zbMath1342.41025OpenAlexW2278184812MaRDI QIDQ290797

Shao-Bo Lin

Publication date: 3 June 2016

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2016.02.003

zbMATH Keywords

linear approximationnonlinear approximationKolmogorov \(n\)-widthpseudo-dimensionspherical radial basis function networks

Mathematics Subject Classification ID

Inequalities in approximation (Bernstein, Jackson, Nikol'ski?-type inequalities) (41A17) Approximation by other special function classes (41A30)

Related Items (1)

ON THE ERROR OF APPROXIMATION BY RBF NEURAL NETWORKS WITH TWO HIDDEN NODES

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A non-linear approximation method on the sphere
• Probabilistic and average widths of Sobolev spaces on compact two-point homogeneous spaces equipped with a Gaussian measure
• Continuous and discrete least-squares approximation by radial basis functions on spheres
• Jackson-type inequalities for spherical neural networks with doubling weights
• On the degree of approximation by manifolds of finite pseudo-dimension
• On best approximation by ridge functions
• Lower bounds for approximation by MLP neural networks
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Fundamental sets of continuous functions on spheres
• Distributing many points on a sphere
• Error bounds for solving pseudodifferential equations on spheres by collocation with zonal kernels
• A general radial quasi-interpolation operator on the sphere
• Approximation in rough native spaces by shifts of smooth kernels on spheres
• On best approximation of classes by radial functions
• Kolmogorov width of classes of smooth functions on the sphere \(\mathbb S^{d-1}\)
• Essential rate for approximation by spherical neural networks
• Approximation properties of zonal function networks using scattered data on the sphere
• Direct and inverse Sobolev error estimates for scattered data interpolation via spherical basis functions
• Almost optimal estimates for best approximation by translates on a torus
• Spherical basis functions and uniform distribution of points on spheres
• Approximation and learning by greedy algorithms
• Pseudo-dimension and entropy of manifolds formed by affine-invariant dictionary
• $L^p$ Bernstein estimates and approximation by spherical basis functions
• Universal approximation bounds for superpositions of a sigmoidal function
• Asymptotics for minimal discrete energy on the sphere
• Lower bounds for multivariate approximation by affine-invariant dictionaries
• Comparison of worst case errors in linear and neural network approximation
• Scattered Data Interpolation on Spheres: Error Estimates and Locally Supported Basis Functions
• A necessary and sufficient condition for strictly positive definite functions on spheres
• Scattered Data Approximation
• Error bounds for approximation with neural networks
• Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory

This page was built for publication: Linear and nonlinear approximation of spherical radial basis function networks