Approximation results for neural network operators activated by sigmoidal functions

DOI10.1016/J.NEUNET.2013.03.015zbMATH Open1296.41017OpenAlexW1986164709WikidataQ51230478 ScholiaQ51230478MaRDI QIDQ459444FDOQ459444

Authors: Danilo Costarelli, Renato Spigler 

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

Recommendations

• Multivariate neural network operators with sigmoidal activation functions
• Approximation by neural networks with sigmoidal functions
• The approximation operators with sigmoidal functions
• Univariate sigmoidal neural newtwork approximation
• The new approximation operators with sigmoidal functions

zbMATH Keywords

Lipschitz classesuniform approximationneural networks operatorssigmoidal functionsorder of approximation

Mathematics Subject Classification ID

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

Cites Work

• Universal approximation bounds for superpositions of a sigmoidal function
• A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization
• Approximation by superpositions of a sigmoidal function
• The construction and approximation of a class of neural networks operators with Ramp functions
• Constructive approximation by superposition of sigmoidal functions
• Title not available (Why is that?)
• The approximation operators with sigmoidal functions
• Uniform approximation by neural networks
• Approximation with neural networks activated by ramp sigmoids
• Approximation by series of sigmoidal functions with applications to neural networks
• Title not available (Why is that?)
• Intelligent systems. Approximation by artificial neural networks
• Approximation by radial bases and neural networks
• Approximation by Ridge functions and neural networks with one hidden layer
• Approximation by superposition of sigmoidal and radial basis functions
• Rate of convergence of some neural network operators to the unit-univariate case
• Degree of approximation by neural and translation networks with a single hidden layer
• Univariate sigmoidal neural newtwork approximation
• Title not available (Why is that?)
• Univariate hyperbolic tangent neural network approximation
• Multivariate hyperbolic tangent neural network approximation
• Multivariate sigmoidal neural network approximation
• Univariant approximation by superpositions of a sigmoidal function
• 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.
• Solving Volterra integral equations of the second kind by sigmoidal functions approximation
• Approximation by superpositions of a sigmoidal function
• Title not available (Why is that?)
• Complexity estimates based on integral transforms induced by computational units
• 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
• Title not available (Why is that?)
• On a Variational Norm Tailored to Variable-Basis Approximation Schemes

Cited In (60)

• Approximation results by multivariate Kantorovich-type neural network sampling operators in Lebesgue spaces with variable exponents
• Some density results by deep Kantorovich type neural network operators
• Multiple general sigmoids based Banach space valued neural network multivariate approximation
• Best approximation and inverse results for neural network operators
• Abstract Voronovskaya type asymptotic expansions for general sigmoid functions based quasi-interpolation neural network operators
• Approximation error of single hidden layer neural networks with fixed weights
• Exponential Sampling Type Kantorovich Max-Product Neural Network Operators
• Asymptotic analysis of neural network operators employing the Hardy-Littlewood maximal inequality
• Neural network interpolation operators based on Lagrange polynomials
• Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients
• Approximation rates for neural networks with encodable weights in smoothness spaces
• On decision regions of narrow deep neural networks
• On sharpness of error bounds for multivariate neural network approximation
• Interpolation by neural network operators activated by ramp functions
• High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
• The construction and approximation of the neural network with two weights
• On the Hausdorff distance between the Heaviside step function and Verhulst logistic function
• Approximation by network operators with logistic activation functions
• Solving numerically nonlinear systems of balance laws by multivariate sigmoidal functions approximation
• On the approximation of functions by tanh neural networks
• The construction and approximation of feedforward neural network with hyperbolic tangent function
• Hyperbolic tangent like relied Banach space valued neural network multivariate approximations
• Approximation by a class of neural network operators on scattered data
• Multivariate neural network operators with sigmoidal activation functions
• Rate of approximation for multivariate sampling Kantorovich operators on some functions spaces
• Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions
• Approximation by perturbed neural network operators
• Approximation problems in sigma-pi neural networks
• An adaptive learning rate backpropagation-type neural network for solving \(n\times n\) systems on nonlinear algebraic equations
• Order of approximation for exponential sampling type neural network operators
• Fractional type multivariate neural network operators
• Approximate solutions of Volterra integral equations by an interpolation method based on ramp functions
• Approximation error for neural network operators by an averaged modulus of smoothness
• Modified neural network operators and their convergence properties with summability methods
• Voronovskaya type asymptotic expansions for perturbed neural network operators
• Approximations by multivariate perturbed neural network operators
• Approximation order to a function in \(L_p\) space by generalized translation networks
• Approximation by exponential sampling type neural network operators
• Quantitative approximation by perturbed Kantorovich-Choquet neural network operators
• Neural network operators: constructive interpolation of multivariate functions
• Degree of approximation for nonlinear multivariate sampling Kantorovich operators on some functions spaces
• Sigmoidal approximations of Heaviside functions in neural lattice models
• Approximation with neural networks activated by ramp sigmoids
• The properties of logistic function and applications to neural network approximation
• A formula for the approximation of functions by single hidden layer neural networks with weights from two straight lines
• On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks
• Sigmoid generators for neural computing using piecewise approximations
• Approximation by series of sigmoidal functions with applications to neural networks
• Convergence of a family of neural network operators of the Kantorovich type
• DENSITY RESULTS BY DEEP NEURAL NETWORK OPERATORS WITH INTEGER WEIGHTS
• Asymptotic expansions and Voronovskaja type theorems for the multivariate neural network operators
• The construction and approximation of a class of neural networks operators with Ramp functions
• Max-product neural network and quasi-interpolation operators activated by sigmoidal functions
• Richards's curve induced Banach space valued multivariate neural network approximation
• Error estimation for approximate solutions of delay Volterra integral equations
• Multivariate neural network interpolation operators
• Quantitative estimates for neural network operators implied by the asymptotic behaviour of the sigmoidal activation functions
• On the approximation of the step function by some sigmoid functions
• Modeling of complex dynamic systems using differential neural networks with the incorporation of a priori knowledge
• Title not available (Why is that?)

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q459444)