Dimension Independent Approximation by Neural Networks: How Can we Cope With the Curse of Dimensionality?
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F00%3A06010168" target="_blank" >RIV/67985807:_____/00:06010168 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Dimension Independent Approximation by Neural Networks: How Can we Cope With the Curse of Dimensionality?
Original language description
In this paper we study feedforward neural networks as nonlinear approximation schemes computing parametrized sets of variable-basis functions. We show that under suitable constraints on the functions be approximated and on the type of hidden units approximation by such networks does not exhibit the curse of dimensionality.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
BA - General mathematics
OECD FORD branch
—
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2000
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Non-Linear Problems in Aviation and Aerospace.
ISBN
—
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
355-364
Publisher name
European Conference Publications
Place of publication
Cambridge
Event location
Daytona Beach [US]
Event date
May 10, 2000
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—