Approximation results for neural network operators activated by sigmoidal functions

DOI10.1016/j.neunet.2013.03.015zbMath1296.41017OpenAlexW1986164709WikidataQ51230478 ScholiaQ51230478MaRDI QIDQ459444

Renato Spigler, Danilo Costarelli

Publication date: 9 October 2014

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2013.03.015

zbMATH Keywords

order of approximationuniform approximationsigmoidal functionsLipschitz classesneural networks operators

Mathematics Subject Classification ID

Approximation by other special function classes (41A30) Approximation by arbitrary linear expressions (41A45)

Related Items (47)

On the Hausdorff distance between the Heaviside step function and Verhulst logistic function ⋮ Approximation by network operators with logistic activation functions ⋮ Max-product neural network and quasi-interpolation operators activated by sigmoidal functions ⋮ DENSITY RESULTS BY DEEP NEURAL NETWORK OPERATORS WITH INTEGER WEIGHTS ⋮ Degree of Approximation for Nonlinear Multivariate Sampling Kantorovich Operators on Some Functions Spaces ⋮ Multivariate neural network interpolation operators ⋮ Solving numerically nonlinear systems of balance laws by multivariate sigmoidal functions approximation ⋮ Neural network operators: constructive interpolation of multivariate functions ⋮ Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions ⋮ Asymptotic expansions and Voronovskaja type theorems for the multivariate neural network operators ⋮ Modified neural network operators and their convergence properties with summability methods ⋮ Quantitative estimates for neural network operators implied by the asymptotic behaviour of the sigmoidal activation functions ⋮ On the approximation of functions by tanh neural networks ⋮ On sharpness of error bounds for multivariate neural network approximation ⋮ On decision regions of narrow deep neural networks ⋮ Approximation by a class of neural network operators on scattered data ⋮ Approximation error for neural network operators by an averaged modulus of smoothness ⋮ Hyperbolic tangent like relied Banach space valued neural network multivariate approximations ⋮ Voronovskaya Type Asymptotic Expansions for Perturbed Neural Network Operators ⋮ Some density results by deep Kantorovich type neural network operators ⋮ Multiple general sigmoids based Banach space valued neural network multivariate approximation ⋮ Fractional type multivariate neural network operators ⋮ The construction and approximation of feedforward neural network with hyperbolic tangent function ⋮ Approximation error of single hidden layer neural networks with fixed weights ⋮ Order of approximation for exponential sampling type neural network operators ⋮ Richards's curve induced Banach space valued multivariate neural network approximation ⋮ Error Estimation for Approximate Solutions of Delay Volterra Integral Equations ⋮ Unnamed Item ⋮ Multivariate neural network operators with sigmoidal activation functions ⋮ On the approximation of the step function by some sigmoid functions ⋮ Rate of approximation for multivariate sampling Kantorovich operators on some functions spaces ⋮ Modeling of complex dynamic systems using differential neural networks with the incorporation of a priori knowledge ⋮ Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients ⋮ Interpolation by neural network operators activated by ramp functions ⋮ Convergence of a family of neural network operators of the Kantorovich type ⋮ Approximation by series of sigmoidal functions with applications to neural networks ⋮ An adaptive learning rate backpropagation‐type neural network for solving n × n systems on nonlinear algebraic equations ⋮ Unnamed Item ⋮ Approximation by exponential sampling type neural network operators ⋮ Approximation rates for neural networks with encodable weights in smoothness spaces ⋮ Quantitative approximation by perturbed Kantorovich-Choquet neural network operators ⋮ On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks ⋮ Approximate solutions of Volterra integral equations by an interpolation method based on ramp functions ⋮ The construction and approximation of the neural network with two weights ⋮ Approximation by perturbed neural network operators ⋮ Approximations by multivariate perturbed neural network operators ⋮ High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Solving Volterra integral equations of the second kind by sigmoidal functions approximation
• A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization
• Intelligent systems. Approximation by artificial neural networks
• Univariate hyperbolic tangent neural network approximation
• Multivariate hyperbolic tangent neural network approximation
• Multivariate sigmoidal neural network approximation
• The approximation operators with sigmoidal functions
• 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
• Univariant approximation by superpositions of a sigmoidal function
• Rate of convergence of some neural network operators to the unit-univariate case
• Approximation order to a function in \(\overline C({\mathbb R})\) by superposition of a sigmoidal function
• Approximation of functions of finite variation by superpositions of a sigmoidal function.
• Degree of approximation by neural and translation networks with a single hidden layer
• Complexity estimates based on integral transforms induced by computational units
• Approximation with neural networks activated by ramp sigmoids
• Approximation by series of sigmoidal functions with applications to neural networks
• A collocation method for solving nonlinear Volterra integro-differential equations of neutral type by sigmoidal functions
• Simultaneous approximations of multivariate functions and their derivatives by neural networks with one hidden layer
• Universal approximation bounds for superpositions of a sigmoidal function
• On a Variational Norm Tailored to Variable-Basis Approximation Schemes
• Constructive Approximation by Superposition of Sigmoidal Functions
• Approximation by superpositions of a sigmoidal function
• Approximation by superpositions of a sigmoidal function
• Approximation by radial bases and neural networks

This page was built for publication: Approximation results for neural network operators activated by sigmoidal functions