Number of the records: 1  

Comparing Fixed and Variable-Width Gaussian Networks

  1. 1.
    SYSNO ASEP0428366
    Document TypeJ - Journal Article
    R&D Document TypeJournal Article
    Subsidiary JČlánek ve WOS
    TitleComparing Fixed and Variable-Width Gaussian Networks
    Author(s) Kůrková, Věra (UIVT-O) RID, SAI, ORCID
    Kainen, P.C. (US)
    Source TitleNeural Networks. - : Elsevier - ISSN 0893-6080
    Roč. 57, September (2014), s. 23-28
    Number of pages6 s.
    Languageeng - English
    CountryGB - United Kingdom
    KeywordsGaussian radial and kernel networks ; Functionally equivalent networks ; Universal approximators ; Stabilizers defined by Gaussian kernels ; Argminima of error functionals
    Subject RIVIN - Informatics, Computer Science
    R&D ProjectsLD13002 GA MŠMT - Ministry of Education, Youth and Sports (MEYS)
    Institutional supportUIVT-O - RVO:67985807
    UT WOS000340319400003
    EID SCOPUS84901602323
    DOI10.1016/j.neunet.2014.05.005
    AnnotationThe 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.
    WorkplaceInstitute of Computer Science
    ContactTereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800
    Year of Publishing2015
Number of the records: 1  

  This site uses cookies to make them easier to browse. Learn more about how we use cookies.