Search results
- 1.0427584 - ÚI 2015 RIV CH eng C - Conference Paper (international conference)
Kůrková, Věra
Representations of Highly-Varying Functions by One-Hidden-Layer Networks.
Artificial Intelligence and Soft Computing Part I. Cham: Springer, 2014 - (Rutkowski, L.; Korytkowski, M.; Scherer, R.; Tadeusiewicz, R.; Zadeh, L.; Zurada, J.), s. 67-76. Lecture Notes in Artificial Intelligence, 8467. ISBN 978-3-319-07172-5. ISSN 0302-9743.
[ICAISC 2014. International Conference on Artificial Intelligence and Soft Computing /13./. Zakopane (PL), 01.06.2014-05.06.2014]
R&D Projects: GA MŠMT(CZ) LD13002
Institutional support: RVO:67985807
Keywords : model complexity of neural networks * one-hidden-layer networks * highly-varying functions * tractability of representations of multivariable functions by neural networks
Subject RIV: IN - Informatics, Computer Science
Permanent Link: http://hdl.handle.net/11104/0233103File Download Size Commentary Version Access a0427584.pdf 1 203.7 KB Publisher’s postprint require - 2.0396115 - ÚI 2014 CZ eng V - Research Report
Kůrková, Věra
Representations of Highly-Varying Functions by One-Hidden-Layer Networks.
Prague: ICS AS CR, 2013. 10 s. Technical Report, V-1187.
R&D Projects: GA MŠMT(CZ) LD13002
Institutional support: RVO:67985807
Keywords : model complexity of neural networks * one-hidden-layer networks * highly-varying functions * tractability of representations of multivariable functions by neural networks
Subject RIV: IN - Informatics, Computer Science
Permanent Link: http://hdl.handle.net/11104/0223955File Download Size Commentary Version Access v1187-13.pdf 0 129.7 KB Author´s preprint require - 3.0360537 - ÚI 2013 RIV DE eng C - Conference Paper (international conference)
Kůrková, Věra
Model Complexity of Neural Networks in High-Dimensional Approximation.
Recent Advances in Intelligent Engineering Systems. Vol. 1. Berlin: Springer, 2012 - (Fodor, S.; Klempous, J.; Suárez Araujo, C.), s. 151-160. Studies in Computational Intelligence, 378. ISBN 978-3-642-23228-2. ISSN 1860-949X.
[INES 2010. International Conference on Intelligent Engineering Systems /14./. Las Palmas de Gran Canaria (ES), 05.05.2010-07.05.2010]
R&D Projects: GA MŠMT OC10047; GA MŠMT MEB040901
Institutional research plan: CEZ:AV0Z10300504
Keywords : model complexity of neural networks * Gaussian radial-basis networks * dependence on input dimension
Subject RIV: IN - Informatics, Computer Science
Permanent Link: http://hdl.handle.net/11104/0198055File Download Size Commentary Version Access a0360537.pdf 0 124.2 KB Publisher’s postprint require - 4.0328415 - ÚI 2010 RIV US eng J - Journal Article
Kainen, P.C. - Kůrková, Věra
An Integral Upper Bound for Neural Network Approximation.
[Integrální horní odhad pro aproximaci neuronovými sítěmi.]
Neural Computation. Roč. 21, č. 10 (2009), s. 2970-2989. ISSN 0899-7667. E-ISSN 1530-888X
R&D Projects: GA MŠMT(CZ) 1M0567
Institutional research plan: CEZ:AV0Z10300504
Keywords : model complexity of neural networks * Bochner integral
Subject RIV: IN - Informatics, Computer Science
Impact factor: 2.175, year: 2009
Permanent Link: http://hdl.handle.net/11104/0174736 - 5.0317780 - ÚI 2009 SIGLE CZ eng V - Research Report
Kainen, P.C. - Kůrková, Věra
An integral upper bound for neural-network approximation.
Prague: ICS AS CR, 2008. 14 s. Technical Report, V-1023.
R&D Projects: GA MŠMT(CZ) 1M0567
Institutional research plan: CEZ:AV0Z10300504
Keywords : model complexity of neural networks * integral representation in the form of network with infinitely many hidden units * rates of variable-basis approximation * variational norm * Bochner integral * perceptron networks
Subject RIV: BA - General Mathematics
Permanent Link: http://hdl.handle.net/11104/0167341File Download Size Commentary Version Access v1023-08.pdf 15 245.9 KB Other open-access