Number of the records: 1
Innovations in Neural Information Paradigms and Applications
- 1.
SYSNO ASEP 0328492 Document Type M - Monograph Chapter R&D Document Type Monograph Chapter Title Estimates of Model Complexity in Neural-Network Learning Title Odhady modelové složitosti při učení neuronových sítí Author(s) Kůrková, Věra (UIVT-O) RID, SAI, ORCID Source Title Innovations in Neural Information Paradigms and Applications. - Berlin : Springer, 2009 / Bianchini M. ; Maggini M. ; Scarselli F. ; Jain L.C - ISBN 978-3-642-04002-3 Pages s. 97-111 Number of pages 15 s. Number of copy 500 Number of pages 294 Language eng - English Country DE - Germany Keywords model complexity ; neural networks ; learning from data 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 000271231000005 EID SCOPUS 70350227066 DOI 10.1007/978-3-642-04003-0_5 Annotation Model complexity in neural-network learning is investigated using tools from nonlinear approximation and integration theory. Estimates of network complexity are obtained from inspection of upper bounds on convergence of minima of error functionals over networks with an increasing number of units to their global minima. The estimates are derived using integral transforms induced by computational units. The role of dimensionality of training data defining error functionals is discussed. 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