Number of the records: 1

Comparison of Approximation Capabilities of Neural Networks and Linear Models

SYSNO ASEP	0348390
Document Type	C - Proceedings Paper (int. conf.)
R&D Document Type	Conference Paper
Title	Comparison of Approximation Capabilities of Neural Networks and Linear Models
Author(s)	Kůrková, Věra (UIVT-O)_{RID, SAI, ORCID}
Source Title	Informačné Technológie - Aplikácie a Teória. - Seňa : Pont, 2010 / Pardubská D. - ISBN 978-80-970179-3-4
Pages	s. 31-36
Number of pages	6 s.
Action	ITAT 2010. Conference on Theory and Practice of Information Technologies
Event date	21.09.2010-25.09.2010
VEvent location	Smrekovica
Country	SK - Slovakia
Event type	EUR
Language	eng - English
Country	SK - Slovakia
Keywords	neural network approximation ; linear approximation
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)
Annotation	Using method from nonlinear approximation and integral representations tailored to computational units, we describe some cases when neural networks outperform any linear approximator.
Workplace	Institute of Computer Science
Contact	Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800
Year of Publishing	2011

Number of the records: 1