The ridge function representation of polynomials and an application to neural networks

DOI10.1007/S10114-011-9407-1zbMath1229.41034OpenAlexW1975824488MaRDI QIDQ644645

Feilong Cao, Tingfan Xie

Publication date: 4 November 2011

Published in: Acta Mathematica Sinica. English Series (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10114-011-9407-1

zbMATH Keywords

neural networkapproximationpolynomialridge function

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32) Multidimensional problems (41A63) Interpolation in approximation theory (41A05)

Related Items (4)

A note on the applications of one primary function in deep neural networks ⋮ Construction and approximation for a class of feedforward neural networks with sigmoidal function ⋮ Approximation of curve-based sleeve functions in high dimensions ⋮ Approximation by sums of ridge functions with fixed directions

Cites Work

• Unnamed Item
• Approximation by polynomials and ridge functions of classes of \(s\)-monotone radial functions
• Error bounds of two smoothing approximations for semi-infinite minimax problems
• Approximation by Ridge functions and neural networks with one hidden layer
• Approximation by superposition of sigmoidal and radial basis functions
• Identifying linear combinations of ridge functions
• On best approximation by ridge functions
• On the approximation of functional classes equipped with a uniform measure using ridge functions
• Fundamentality of ridge functions
• On approximation by ridge functions
• Degree of approximation by neural and translation networks with a single hidden layer
• On the representation by linear superpositions
• On Nonlinear Functions of Linear Combinations
• Universal approximation bounds for superpositions of a sigmoidal function
• Bounds on rates of variable-basis and neural-network approximation
• Approximation by superpositions of a sigmoidal function
• Error bounds for approximation with neural networks

This page was built for publication: The ridge function representation of polynomials and an application to neural networks