An approximation by neural networks with a fixed weight (Q1767906): Difference between revisions
From MaRDI portal
Set OpenAlex properties. |
Normalize DOI. |
||
(One intermediate revision by one other user not shown) | |||
Property / DOI | |||
Property / DOI: 10.1016/j.camwa.2003.06.008 / rank | |||
Property / cites work | |||
Property / cites work: Extension of localised approximation by neural networks / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Universal approximation bounds for superpositions of a sigmoidal function / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4011460 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Approximation by Ridge functions and neural networks with one hidden layer / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Approximation by superpositions of a sigmoidal function / rank | |||
Normal rank | |||
Property / DOI | |||
Property / DOI: 10.1016/J.CAMWA.2003.06.008 / rank | |||
Normal rank |
Latest revision as of 09:52, 11 December 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | An approximation by neural networks with a fixed weight |
scientific article |
Statements
An approximation by neural networks with a fixed weight (English)
0 references
8 March 2005
0 references
A function \(\sigma: {\mathbb R} \to {\mathbb R}\) is called sigmoidal if \(\lim_ {x\to -\infty} \sigma(x)=0\), \(\lim_ {x\to +\infty} \sigma(x)=1\). Theorem 1. Let \(\sigma\) be a bounded sigmoidal function on \({\mathbb R}\) and let \(\epsilon >0\) be given. If \(f\) is a continuous function on \({\mathbb R}\) such that \(\lim_{| x| \to \infty} f(x)=0\), then there exist constants \(b_i, c_i \in {\mathbb R}\) and positive integers \(N,K\) such that \[ \left | f(x)-\sum_{i=1}^N c_i \sigma (Kx+b_i)\right | <\epsilon, \qquad x \in {\mathbb R}. \] Another similar theorem is also proved and some numerical examples are given.
0 references
neural network
0 references
sigmoidal function
0 references
convolution
0 references