All
All

What are you looking for?

All
Projects
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Testing Error Estimates for Regularization and Radial Function Networks

Result description

Radial basis function networks (RBF) can be seen as a special case of regularization networks with a selection of learning algorithms. We study a relationship between RN and RBF, and experimentally evaluate their approximation and generalization ability.

Keywords

regularizationradial basis function networksgeneralization

The result's identifiers

Alternative languages

  • Result language

    angličtina

  • Original language name

    Testing Error Estimates for Regularization and Radial Function Networks

  • Original language description

    Radial basis function networks (RBF) can be seen as a special case of regularization networks with a selection of learning algorithms. We study a relationship between RN and RBF, and experimentally evaluate their approximation and generalization ability.

  • Czech name

    Testování odhadů chyb pro regularizační a RBF sítě

  • Czech description

    RBF sítě lze chápat jako speciální případ regularizačních sítí s většími možnostmi učících algoritmů. Studujeme vztah regularizačních a RBF sítí a experimentálně ověřujeme jejich aproximační a generalizační vlastnosti.

Classification

  • Type

    D - Article in proceedings

  • CEP classification

    IN - Informatics

  • OECD FORD branch

Result continuities

Others

  • Publication year

    2008

  • Confidentiality

    S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Data specific for result type

  • Article name in the collection

    Advances in Neural Networks - ISNN 2008

  • ISBN

    978-3-540-87731-8

  • ISSN

  • e-ISSN

  • Number of pages

    6

  • Pages from-to

  • Publisher name

    Springer

  • Place of publication

    Berlin

  • Event location

    Beijing

  • Event date

    Sep 24, 2008

  • Type of event by nationality

    WRD - Celosvětová akce

  • UT code for WoS article

    000260660500061