Number of the records: 1
Model Complexity of Neural Networks in High-Dimensional Approximation
- 1.
SYSNO ASEP 0360537 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Model Complexity of Neural Networks in High-Dimensional Approximation Author(s) Kůrková, Věra (UIVT-O) RID, SAI, ORCID Source Title Recent Advances in Intelligent Engineering Systems, Foundation of Computational Intelligence, 1. - Berlin : Springer, 2012 / Fodor S. ; Klempous J. ; Suárez Araujo C.P. - ISSN 1860-949X - ISBN 978-3-642-23228-2 Pages s. 151-160 Number of pages 10 s. Number of pages 451 Publication form Print - P Action INES 2010. International Conference on Intelligent Engineering Systems /14./ Event date 05.05.2010-07.05.2010 VEvent location Las Palmas de Gran Canaria Country ES - Spain Event type WRD Language eng - English Country DE - Germany Keywords model complexity of neural networks ; Gaussian radial-basis networks ; dependence on input dimension Subject RIV IN - Informatics, Computer Science R&D Projects OC10047 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) MEB040901 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) CEZ AV0Z10300504 - UIVT-O (2005-2011) UT WOS 000307313000007 EID SCOPUS 82255191250 DOI 10.1007/978-3-642-23229-9_7 Annotation The role of dimensionality in approximation by neural networks is investigated. Methods from nonlinear approximation theory are used to describe sets of functions which can be approximated by neural networks with a polynomial dependence of model complexity on the input dimension. The results are illustrated by examples of Gaussian radial networks. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2013
Number of the records: 1