An Integral Upper Bound for Neural Network Approximation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F09%3A00328415" target="_blank" >RIV/67985807:_____/09:00328415 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

An Integral Upper Bound for Neural Network Approximation

Original language description

For functions with suitable integral representations in the form of networks with infinitely many hidden units, upper bounds are derived on the speed of decrease of approximation error as the number of network units increases. These bounds are obtained using the framework of Bochner.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

IN - Informatics

OECD FORD branch

—

Project

<a href="/en/project/1M0567" target="_blank" >1M0567: Centre for Applied Cybernetics</a><br>

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2009

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Neural Computation

ISSN

0899-7667

e-ISSN

—

Volume of the periodical

21

Issue of the periodical within the volume

10

Country of publishing house

US - UNITED STATES

Number of pages

20

Pages from-to

—

UT code for WoS article

000269833200010

EID of the result in the Scopus database

—