Number of the records: 1
Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
- 1.
SYSNO ASEP 0368521 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks Author(s) Kainen, P.C. (US)
Kůrková, Věra (UIVT-O) RID, SAI, ORCID
Sanguineti, M. (IT)Source Title IEEE Transactions on Information Theory. - : Institute of Electrical and Electronics Engineers - ISSN 0018-9448
Roč. 58, č. 2 (2012), s. 1203-1214Number of pages 12 s. Language eng - English Country US - United States Keywords dictionary-based computational models ; high-dimensional approximation and optimization ; model complexity ; polynomial upper bounds Subject RIV IN - Informatics, Computer Science R&D Projects ME10023 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) GA201/08/1744 GA ČR - Czech Science Foundation (CSF) GAP202/11/1368 GA ČR - Czech Science Foundation (CSF) CEZ AV0Z10300504 - UIVT-O (2005-2011) UT WOS 000300246900047 EID SCOPUS 84856932727 DOI 10.1109/TIT.2011.2169531 Annotation The role of input dimension is studied in approximating, in various norms, target sets of d-variable functions using linear combinations of adjustable computational units. Results are applied to approximation and solution of optimization problems by neural networks with perceptron and Gaussian radial computational units. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2012
Number of the records: 1