Approximation problems in system identification with neural networks (Q1334039)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Approximation problems in system identification with neural networks |
scientific article |
Statements
Approximation problems in system identification with neural networks (English)
0 references
19 September 1994
0 references
The capability of approximating continuous functions of several variables by neural nets is investigated. Starting from a result by Cybenko concerning the denseness of linear combinations of continuous sigmoidal functions in \(L^ p (K)\), the author finally proves -- in the framework of \(L^ p\)-Tauber-Wiener functions -- that by composition of some functions of one variable, one can approximate continuous functionals defined on compact \(L^ p (K)\), and continuous operators from compact \(L^ p (K_ 1)\) to \(L^ p (K_ 2)\).
0 references
neural nets
0 references