Number of the records: 1
An Integral Upper Bound for Neural Network Approximation
- 1.
SYSNO ASEP 0328415 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title An Integral Upper Bound for Neural Network Approximation Title Integrální horní odhad pro aproximaci neuronovými sítěmi Author(s) Kainen, P.C. (US)
Kůrková, Věra (UIVT-O) RID, SAI, ORCIDSource Title Neural Computation - ISSN 0899-7667
Roč. 21, č. 10 (2009), s. 2970-2989Number of pages 20 s. Language eng - English Country US - United States Keywords model complexity of neural networks ; Bochner integral Subject RIV IN - Informatics, Computer Science R&D Projects 1M0567 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) CEZ AV0Z10300504 - UIVT-O (2005-2011) UT WOS 000269833200010 EID SCOPUS 70350222271 DOI 10.1162/neco.2009.04-08-745 Annotation 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. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2010
Number of the records: 1