Skip to main content

COKOS: A COprocessor for KOhonen’s Selforganizing Map

  • Conference paper
  • First Online:
ICANN ’93 (ICANN 1993)

Abstract

In this paper we present a system which enables easy and fast computation of Kohonen’s selforganizing map (SOM). It is a hardware supported system consisting of different parts. A neural coprocessor (COKOS) is connected to a personal computer (PC) by a special, asynchronous interface. The neural coprocessor works vector-component-parallel and processing-element-serial and speeds up the performance of Kohonen’s algorithm of the selforganizing map by magnitude. An userfriendly interface supports the preprocessing of the input data and the control and assessment of the learning process.

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 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight 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.

References

  1. I. Barth, T. Bräunl, S. Engelhardt, und F. Sembach. Parallaxis version 2 user manual. Technical Report 2/91, University of Stuttgart, 1991.

    Google Scholar 

  2. J. Göppert, H. Speckmann, W. Rosenstiel, W. Kessler, G. Kraus, und G. Gauglitz. Evaluation of Spectra in Chemistry and Physics with Kohonen’s Selforganizing Feature Map. In Neuronimes 92, 1992.

    Google Scholar 

  3. T. Kohonen. Self-Organization and Associative Memory. Springer Verlag Heidelberg New York Tokyo, 1984.

    MATH  Google Scholar 

  4. T. Kohonen. The Neural Phonetic Typewriter. IEEE Computer, Seiten 11–22, March 1988.

    Google Scholar 

  5. D. Niebur und A.J. Germond. Power System Static Security Assessment Using the Kohonen Neural Network Classi lier. In IEEE Power Industry Computer Applications Conference, 1991.

    Google Scholar 

  6. H. Speckmann, P. Thole, und W. Rosenstiel. Hardware Implementations of Kohonen’s Selforganizing Feature Map. In IJCNN 92, Bejing, China, Seiten III 183–187, 1992.

    Chapter  Google Scholar 

  7. V. Tryba. Selbstorganisierende Karten: Theorie, Anwendung und VLSI-Implementierung. VDI Verlag, 1992.

    Google Scholar 

  8. A. Ultsch und H. P. Siemon. Exploratory Data Analysis: Using Kohonen Networks on Transputers. Technical report, Universität Dortmund, 1989.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag London Limited

About this paper

Cite this paper

Speckmann, H., Thole, P., Rosenstiel, W. (1993). COKOS: A COprocessor for KOhonen’s Selforganizing Map. In: Gielen, S., Kappen, B. (eds) ICANN ’93. ICANN 1993. Springer, London. https://doi.org/10.1007/978-1-4471-2063-6_309

Download citation

  • DOI: https://doi.org/10.1007/978-1-4471-2063-6_309

  • Published:

  • Publisher Name: Springer, London

  • Print ISBN: 978-3-540-19839-0

  • Online ISBN: 978-1-4471-2063-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics