Tight Bounds on Rates of Neural-Network Approximation.
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F01%3A06010102" target="_blank" >RIV/67985807:_____/01:06010102 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Tight Bounds on Rates of Neural-Network Approximation.
Original language description
Complexity of neural networks measured by the number of hidden units is studied in terms of rates of approximation. Limitations of improvements of upper bounds of the order of O(n exp(-1/2)) on such rates are investigated for perceptron networks with some periodic and some sigmoidal activation functions.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
BA - General mathematics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA201%2F00%2F1489" target="_blank" >GA201/00/1489: Soft Computing: Theoretical foundations and experiments</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2001
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Artificial Neural Networks - ICANN'2001.
ISBN
3-540-42486-5
ISSN
—
e-ISSN
—
Number of pages
12
Pages from-to
277-288
Publisher name
Springer-Verlag
Place of publication
Berlin
Event location
Vienna [AT]
Event date
Aug 21, 2001
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—