Repository logo
  • English
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Log In
    New user? Click here to register.
Repository logo

Repositorio Institucional de la Universidad de Murcia

Repository logoRepository logo
  • Communities & Collections
  • All of DSpace
  • menu.section.collectors
  • menu.section.acerca
  • English
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Log In
    New user? Click here to register.
  1. Home
  2. Browse by Subject

Browsing by Subject "Feedforward neural networks"

Now showing 1 - 1 of 1
Results Per Page
Sort Options
  • Loading...
    Thumbnail Image
    Publication
    Open Access
    Negative results for approximation using single layer and multilayer feedforward neural networks
    (Elsevier, 2021-02-01) Almira, José M.; López-de-Teruel, Pedro E.; Romero-López, Diego J.; Voigtlaender, Felix; Ingeniería y Tecnología de Computadores
    We prove a negative result for the approximation of functions defined on compact subsets of R^d (where d >=2) using feedforward neural networks with one hidden layer and arbitrary continuous activation function. In a nutshell, this result claims the existence of target functions that are as difficult to approximate using these neural networks as one may want. We also demonstrate an analogous result (for general d in N) for neural networks with an arbitrary number of hidden layers, for activation functions that are either rational functions or continuous splines with finitely many pieces.

DSpace software copyright © 2002-2026 LYRASIS

  • Cookie settings
  • Accessibility
  • Send Feedback