Počet záznamů: 1  

Comparing Fixed and Variable-Width Gaussian Networks

  1. 1.
    SYSNO ASEP0428366
    Druh ASEPJ - Článek v odborném periodiku
    Zařazení RIVJ - Článek v odborném periodiku
    Poddruh JČlánek ve WOS
    NázevComparing Fixed and Variable-Width Gaussian Networks
    Tvůrce(i) Kůrková, Věra (UIVT-O) RID, SAI, ORCID
    Kainen, P.C. (US)
    Zdroj.dok.Neural Networks. - : Elsevier - ISSN 0893-6080
    Roč. 57, September (2014), s. 23-28
    Poč.str.6 s.
    Jazyk dok.eng - angličtina
    Země vyd.GB - Velká Británie
    Klíč. slovaGaussian radial and kernel networks ; Functionally equivalent networks ; Universal approximators ; Stabilizers defined by Gaussian kernels ; Argminima of error functionals
    Vědní obor RIVIN - Informatika
    CEPLD13002 GA MŠMT - Ministerstvo školství, mládeže a tělovýchovy
    Institucionální podporaUIVT-O - RVO:67985807
    UT WOS000340319400003
    EID SCOPUS84901602323
    DOI10.1016/j.neunet.2014.05.005
    AnotaceThe role of width of Gaussians in two types of computational models is investigated: Gaussian radial basis- functions (RBFs) where both widths and centers vary and Gaussian kernel networks which have fixed widths but varying centers. The effect of width on functional equivalence, universal approximation property, and form of norms in reproducing kernel Hilbert spaces (RKHSs)is explored. It is proven that if two Gaussian RBF networks have the same input–output functions, then they must have the same numbers of units with the same centers and widths. Further, it is shown that while sets of input–output functions of Gaussian kernel networks with two different widths are disjoint, each such set is large enough to be a universal approximator. Embedding of RKHSs induced by ‘‘flatter’’ Gaussians into RKHSs induced by ‘‘sharper’’ Gaussians is described and growth of the ratios of norms on these spaces with increasing input dimension is estimated. Finally, large sets of argminima of error functionals in sets of input–output functions of Gaussian RBFs are described.
    PracovištěÚstav informatiky
    KontaktTereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800
    Rok sběru2015
Počet záznamů: 1  

  Tyto stránky využívají soubory cookies, které usnadňují jejich prohlížení. Další informace o tom jak používáme cookies.