Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems.
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. Research Abstract Details
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. Abstract Text:
The purpose of this paper is to investigate neural network capability systematically. The main results are: 1) every Tauber-Wiener function is qualified as an activation function in the hidden layer of a three-layered neural network; 2) for a continuous function in S'(R(1 )) to be a Tauber-Wiener function, the necessary and sufficient condition is that it is not a polynomial; 3) the capability of approximating nonlinear functionals defined on some compact set of a Banach space and nonlinear operators has been shown; and 4) the possibility by neural computation to approximate the output as a whole (not at a fixed point) of a dynamical system, thus identifying the system.
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. Publishing Authors By Initials
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. Journal Published:
PUBLICATION TYPE: Journal Article
Journal: IEEE transactions on neural networks / a publicati
VOLUME: 6
Page Numbers: 911-7
Journal Abbreviation:
ISSN: 1045-9227
DAY: 11
MONTH: 02
YEAR: 1995
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. Information
Number of References:
LANGUAGE: eng
NlmUniqueID: 101211035
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. Keywords Mesh Terms:
KEYWORDS:
MESH TERMS:
Chemical & Substance for Abstract: Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. Information
Substance Name:
Registry Number:
Grant and Affiliation Information for Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems.
AFFILIATION: Dept. of Math., Fudan Univ., Shanghai.
Country: United States
AGENCY:
GRANT:
ACRONYM:
MEDLINETA: IEEE Trans Neural Netw
REFSOURCE:
DATABASENAME:
ACCESSION NUMBER:
Number Hits: 0
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems Related Publications