Approximation with neural networks activated by ramp sigmoids (Q1958429)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 5793307
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Approximation with neural networks activated by ramp sigmoids |
scientific article; zbMATH DE number 5793307 |
Statements
Approximation with neural networks activated by ramp sigmoids (English)
0 references
29 September 2010
0 references
One proves that functions defined on a \(d\)-dimensional domain \(S\), with bounded variation with respect to a class of ellipsoids contained in \(S\) , can be accurately approximated by two-hidden-layer feedforward neural networks. The approximation error depends on the number of neurons in both hidden layers, space dimension and function variation. As activation function the rump sigmoid is considered. The author extensively refers to his earlier paper: \textit{G. H. L. Cheang} and \textit{A. R. Barron} in [J. Approximation Theory 104, No.~2, 183--203 (2000; Zbl 0991.41012)].
0 references
two-hidden-layer neural net
0 references
ramp sigmoid
0 references
approximation error bounds
0 references
0 references
0 references
0.94963586
0 references
0 references
0.93500096
0 references
0.93472034
0 references
0.92057824
0 references
0.91529036
0 references
0.9149558
0 references
0.9091351
0 references
0.90736884
0 references
