Constructive Approximation by Superposition of Sigmoidal Functions
From MaRDI portal
Publication:5399935
DOI10.4208/ata.2013.v29.n2.8zbMath1299.41033OpenAlexW1551553193WikidataQ127821367 ScholiaQ127821367MaRDI QIDQ5399935
Renato Spigler, Danilo Costarelli
Publication date: 28 February 2014
Published in: Analysis in Theory and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.4208/ata.2013.v29.n2.8
Related Items (24)
On the Hausdorff distance between the Heaviside step function and Verhulst logistic function ⋮ Approximation by network operators with logistic activation functions ⋮ A new class of activation functions. Some related problems and applications ⋮ Max-product neural network and quasi-interpolation operators activated by sigmoidal functions ⋮ Multivariate neural network interpolation operators ⋮ Uniform approximation rates and metric entropy of shallow neural networks ⋮ Solving numerically nonlinear systems of balance laws by multivariate sigmoidal functions approximation ⋮ A sigmoid method for some nonlinear Fredholm integral equations of the second kind ⋮ Neural network operators: constructive interpolation of multivariate functions ⋮ An interval uncertainty analysis method for structural response bounds using feedforward neural network differentiation ⋮ Solving Volterra integral equations of the second kind by sigmoidal functions approximation ⋮ On the approximation by single hidden layer feedforward neural networks with fixed weights ⋮ Some density results by deep Kantorovich type neural network operators ⋮ The construction and approximation of feedforward neural network with hyperbolic tangent function ⋮ Error Estimation for Approximate Solutions of Delay Volterra Integral Equations ⋮ Approximation results for neural network operators activated by sigmoidal functions ⋮ A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function ⋮ Multivariate neural network operators with sigmoidal activation functions ⋮ A collocation method for solving nonlinear Volterra integro-differential equations of neutral type by sigmoidal functions ⋮ 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 ⋮ On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks ⋮ Bifurcation in car-following models with time delays and driver and mechanic sensitivities
This page was built for publication: Constructive Approximation by Superposition of Sigmoidal Functions
