Approximation by neural networks with sigmoidal functions

DOI10.1007/s10114-013-1730-2zbMath1311.41015OpenAlexW2108930884MaRDI QIDQ381075

Dansheng Yu

Publication date: 15 November 2013

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

Full work available at URL: https://doi.org/10.1007/s10114-013-1730-2

zbMATH Keywords

simultaneous approximationsigmoidal functionsfeedforward neural networkscombinations

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Rate of convergence, degree of approximation (41A25) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (8)

On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights ⋮ Neural network interpolation operators activated by smooth ramp functions ⋮ Modified neural network operators and their convergence properties with summability methods ⋮ Computational homogenization of nonlinear elastic materials using neural networks ⋮ Neural network interpolation operators optimized by Lagrange polynomial ⋮ Neural network interpolation operators of multivariate functions ⋮ The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks ⋮ Rates of approximation by neural network interpolation operators

Cites Work

• Unnamed Item
• The essential order of approximation for neural networks
• The approximation operators with sigmoidal functions
• On approximation by polynomials and rational functions in Orlicz spaces
• Approximation by Ridge functions and neural networks with one hidden layer
• Approximation by superposition of sigmoidal and radial basis functions
• Uniform approximation by neural networks
• Rate of convergence of some neural network operators to the unit-univariate case
• Multilayer feedforward networks are universal approximators
• An approximation by neural networks with a fixed weight
• Degree of approximation by neural and translation networks with a single hidden layer
• Universal approximation bounds for superpositions of a sigmoidal function
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Approximation by neural networks with sigmoidal functions