Skip to main content

Informative Feature Selection in Multilayer Neural Networks

  • Chapter
Neural Networks Theory
  • 3233 Accesses

Abstract

The problem of the informative feature selection is an independent problem in pattern recognition theory, and it has not yet been solved up to now. The existence approaches to this solution and description of so-called structural methods based on the multilayer neural network pattern recognition systems synthesis [14-1], [14-2] are discussed in this book.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literature

  1. Galushkin AI (1974) Synthesis of multilayer pattern recognition systems. Moscow, Energiya, p 367

    Google Scholar 

  2. Galushkin AI (1996) Summary and perspectives of the multilayer neural network theory development (1965–1995) in the proceedings of the Neurocomputer scientific center. Moscow

    Google Scholar 

Download references

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

(2007). Informative Feature Selection in Multilayer Neural Networks. In: Neural Networks Theory. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-48125-6_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-48125-6_15

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-48124-9

  • Online ISBN: 978-3-540-48125-6

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics