• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Echo state networks with sparse output connections
 
  • Details
  • Full
Options
2010
Conference Paper
Title

Echo state networks with sparse output connections

Abstract
An Echo State Network transforms an incoming time series signal into a high-dimensional state space, and, of course, not every dimension may contribute to the solution. We argue that giving low weights via linear regression is not sufficient. Instead irrelevant features should be entirely excluded from directly contributing to the output nodes. We conducted several experiments using two state-of-the-art feature selection algorithms. Results show significant reduction of the generalization error.
Author(s)
Kobialka, Hans-Ulrich  
Kayani, U.
Mainwork
Artificial neural networks - ICANN 2010. 20th international conference. Pt.1  
Conference
International Conference on Artificial Neural Networks (ICANN) 2010  
DOI
10.1007/978-3-642-15819-3_47
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Keyword(s)
  • echo state network

  • feature selection

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024