Počet záznamů: 1
Estimates of Approximation Rates by Gaussian Radial-Basis Functions
- 1.0339929 - ÚI 2010 RIV DE eng C - Konferenční příspěvek (zahraniční konf.)
Kainen, P.C. - Kůrková, Věra - Sanguineti, M.
Estimates of Approximation Rates by Gaussian Radial-Basis Functions.
Adaptive and Natural Computing Algorithms. Vol. 2. Berlin: Springer, 2007 - (Beliczynski, B.; Dzielinski, A.; Iwanowski, M.; Ribeiro, B.), s. 11-18. Lecture Notes in Computer Science, 4432. ISBN 978-3-540-71590-0.
[ICANNGA'2007 /8./. Warsaw (PL), 11.04.2007-14.04.2007]
Grant CEP: GA ČR GA201/05/0557
Výzkumný záměr: CEZ:AV0Z10300504
Klíčová slova: Gaussian Radial-basis function networks * network complexity * smoothing operators
Kód oboru RIV: IN - Informatika
Rates of approximation by networks with Gaussian RBFs with warying widths are investigated. For certain smooth functions, upper bounds are derived in terms of a Sobolev-equivalent norm. Coefficients involved are exponentially decreasing in the dimension. The estimates are proven using Bessel potentials as auxiliary approximating functions.
Trvalý link: http://hdl.handle.net/11104/0183298
Počet záznamů: 1