Bounds on Rates af Approximation by Neural Networks in Lp-spaces.

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F03%3A06030124" target="_blank" >RIV/67985807:_____/03:06030124 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Bounds on Rates af Approximation by Neural Networks in Lp-spaces.

Original language description

We derive upper bounds on rates of convergence of neural network approximation in Lp-spaces. Our bound are based on a version of Maurey-Jones-Barron Theorem for Lp-spaces. They are established in terms of L1-norm of a weight function in a neural networkwith continuum of hidden units representing the function to be approximated.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

BA - General mathematics

OECD FORD branch

—

Project

<a href="/en/project/GA201%2F02%2F0428" target="_blank" >GA201/02/0428: Nonlinear approximation with variable basis and neural networks</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2003

Confidentiality

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

Article name in the collection

Artificial Neural Nets and Genetic Algorithms.

ISBN

3-211-00743-1

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

23-27

Publisher name

Springer-Verlag

Place of publication

Wien

Event location

Roanne [FR]

Event date

Apr 23, 2003

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—