Approximation by superpositions of a sigmoidal function (Q5917524): Difference between revisions
From MaRDI portal
Set profile property. |
ReferenceBot (talk | contribs) Changed an Item |
||
Property / cites work | |||
Property / cites work: Universal approximation bounds for superpositions of a sigmoidal function / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Approximation by superpositions of a sigmoidal function / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Multilayer feedforward networks are universal approximators / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Univariant approximation by superpositions of a sigmoidal function / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training / rank | |||
Normal rank |
Revision as of 19:33, 6 June 2024
scientific article; zbMATH DE number 2096457
Language | Label | Description | Also known as |
---|---|---|---|
English | Approximation by superpositions of a sigmoidal function |
scientific article; zbMATH DE number 2096457 |
Statements
Approximation by superpositions of a sigmoidal function (English)
0 references
6 September 2004
0 references
The present paper deals with the generalization of a result due to \textit{B. Gao} and \textit{Y. Xu} [J. Math. Anal. Appl. 178, 221--226 (1993; Zbl 0783.41016)], concerning the approximation of functions of bounded variation by the linear combinations of a fixed sigmoidal function to the class of functions of bounded phi-variation. Actually the approximation of functions by superpositions of a sigmoidal function has many applications in neural network. In this paper the authors obtained only one dimensional result.
0 references
Hölder continuity property
0 references
sigmoidal function
0 references
phi-variation, uniform approximation
0 references