Complexity of Gaussian-radial-basis networks approximating smooth functions (Q998978): Difference between revisions

From MaRDI portal
ReferenceBot (talk | contribs)
Changed an Item
Normalize DOI.
 
Property / DOI
 
Property / DOI: 10.1016/j.jco.2008.08.001 / rank
Normal rank
 
Property / DOI
 
Property / DOI: 10.1016/J.JCO.2008.08.001 / rank
 
Normal rank

Latest revision as of 03:13, 28 December 2024

scientific article
Language Label Description Also known as
English
Complexity of Gaussian-radial-basis networks approximating smooth functions
scientific article

    Statements

    Complexity of Gaussian-radial-basis networks approximating smooth functions (English)
    0 references
    0 references
    0 references
    0 references
    30 January 2009
    0 references
    The authors approximate smooth functions on \(\mathbb R^d\) by Gaussian radial-basis function networks with units of varying widths, using \(L^2\)-distance with respect to the Lebesgue measure and derive upper bounds of rates of approximation in terms of the Bessel or Sobolev norm of the functions which are approximated. The estimates hold for all numbers of hidden unities and all degrees \(r>d/2\) of Bessel potentials. Moreover, consequences for tractability of multivariable approximation by these networks are discussed.
    0 references
    0 references
    approximate smooth functions
    0 references
    Gaussian-radial-basis-function networks
    0 references
    rates of approximation
    0 references
    model complexity
    0 references
    variation norms
    0 references
    Bessel and Sobolev norms
    0 references
    tractability of approximation
    0 references
    multivariable approximation
    0 references

    Identifiers