Number of the records: 1
Comparison of Approximation Capabilities of Neural Networks and Linear Models
- 1.0348390 - ÚI 2011 RIV SK eng C - Conference Paper (international conference)
Kůrková, Věra
Comparison of Approximation Capabilities of Neural Networks and Linear Models.
Informačné Technológie - Aplikácie a Teória. Seňa: Pont, 2010 - (Pardubská, D.), s. 31-36. ISBN 978-80-970179-3-4.
[ITAT 2010. Conference on Theory and Practice of Information Technologies. Smrekovica (SK), 21.09.2010-25.09.2010]
R&D Projects: GA MŠMT(CZ) 1M0567
Institutional research plan: CEZ:AV0Z10300504
Keywords : neural network approximation * linear approximation
Subject RIV: IN - Informatics, Computer Science
Using method from nonlinear approximation and integral representations tailored to computational units, we describe some cases when neural networks outperform any linear approximator.
Permanent Link: http://hdl.handle.net/11104/0188937
File Download Size Commentary Version Access a0348390.pdf 0 294 KB Publisher’s postprint require
Number of the records: 1