Sciweavers

ICANNGA
2007
Springer

Estimates of Approximation Rates by Gaussian Radial-Basis Functions

13 years 10 months ago
Estimates of Approximation Rates by Gaussian Radial-Basis Functions
Rates of approximation by networks with Gaussian RBFs with varying 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.
Paul C. Kainen, Vera Kurková, Marcello Sang
Added 08 Jun 2010
Updated 08 Jun 2010
Type Conference
Year 2007
Where ICANNGA
Authors Paul C. Kainen, Vera Kurková, Marcello Sanguineti
Comments (0)