Approximation by series of sigmoidal functions with applications to neural networks (Q2255377)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Approximation by series of sigmoidal functions with applications to neural networks |
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Approximation by series of sigmoidal functions with applications to neural networks |
scientific article |
Statements
Approximation by series of sigmoidal functions with applications to neural networks (English)
0 references
9 February 2015
0 references
The authors develop a theory of uniform approximation of functions of certain classes by series of sigmoidal functions, i.e., functions \(\sigma\) on \({\mathbb R}\) such that \[ \lim_{x\to-\infty}\sigma(x)=0\quad\text{and}\quad\lim_{x\to\infty}\sigma(x)=1. \]
0 references
sigmoidal functions
0 references
neural networks
0 references
truncation error
0 references
multiresolution approximation
0 references
wavelet-scaling functions
0 references
