Approximation of functions of finite variation by superpositions of a sigmoidal function.

DOI10.1016/j.aml.2003.11.006zbMath1067.41013OpenAlexW2011090143MaRDI QIDQ1767196

Giuseppe Marino, Grzegorz Lewicki

Publication date: 7 March 2005

Published in: Applied Mathematics Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.aml.2003.11.006

zbMATH Keywords

Lipschitz conditionsigmoidal functionrate of approximationfunction of finite variation

Mathematics Subject Classification ID

Absolutely continuous real functions of several variables, functions of bounded variation (26B30) Approximation by other special function classes (41A30)

Related Items

Uniform approximation rates and metric entropy of shallow neural networks, Neural network interpolation operators activated by smooth ramp functions, Solving Volterra integral equations of the second kind by sigmoidal functions approximation, Nonlinear approximation via compositions, Smoothing tautologies, hidden dynamics, and sigmoid asymptotics for piecewise smooth systems, Approximation results for neural network operators activated by sigmoidal functions, Multivariate neural network operators with sigmoidal activation functions, A collocation method for solving nonlinear Volterra integro-differential equations of neutral type by sigmoidal functions, Deep Network Approximation Characterized by Number of Neurons, Interpolation by neural network operators activated by ramp functions, Approximation by series of sigmoidal functions with applications to neural networks, CONSTRUCTIVE APPROXIMATION BY NEURAL NETWORKS WITH POSITIVE INTEGER WEIGHTS, On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks

Cites Work

• Unnamed Item
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• On the realization of discriminant functions by means of multilayer perceptrons
• Univariant approximation by superpositions of a sigmoidal function
• An analog of the Jackson-Nikol'skij theorem on the approximation by superpositions of sigmoidal functions
• Approximation order to a function in \(\overline C({\mathbb R})\) by superposition of a sigmoidal function
• Universal approximation bounds for superpositions of a sigmoidal function
• Approximation by superpositions of a sigmoidal function
• On sigmoidal functions