Skip to main content
SpringerLink
Log in

Das Lernen von mehrdeutigen Abbildungen mit fehlergesteuerter Zerlegung

  • Conference paper
Book cover Informatik in den Biowissenschaften

Part of the book series: Informatik aktuell ((INFORMAT))

  • 51 Accesses

Abstract

Die gängigen konnektionistischen Lernverfahren scheinen für einfache Probleme gut geeignet zu sein, versagen jedoch bei der Anwendung auf komplexe, reale Aufgaben — wie die Echtzeit-Roboterkontrolle. Bereits bei vielen anderen Anwendungen hat sich das devide and conquer Prinzip als mächtiges Konzept gezeigt, welches die Komplexität von Lernproblemen reduzieren kann[JJB90, Wai89, MT90].

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 54.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 69.99
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.

Literatur

  1. M. Bercovier and T. Pat. A C0 finite element method for the analysis of inextensible pipe lines. Computers and Structures, 18(6):1019–1023, 1984.

    Article  Google Scholar 

  2. G. Farin. Curves and Surfaces for Computer Aided Geometric Design. Academic Press, San Diego, 1990.

    Google Scholar 

  3. D. Fox, V. Heinze, K. Möller, S.B. Thrun and G. Veenker. Learning by error-driven decomposition. In O. Simula, editor, Proceedings of International Conference on Artificial Neural Networks (to appear), Amsterdam, 1991. Elsevier Publisher.

    Google Scholar 

  4. E. Horowitz and S. Salmi. Fundamentals of Computer Algorithms. Computer Science Press, Rockville, 1978.

    Google Scholar 

  5. R. A. Jacobs, M. I. Jordan, and A. G. Barto. Task decomposition through competition in a modular connectionist architecture: The what and where vision task. Technical Report COINS TR 90-27, Dept. of Brain and Cognitive Science, Massachusetts Institute of Technology, Cambridge,MA, 1990.

    Google Scholar 

  6. M. I. Jordan. Generic constraints on unspecified target constraints. In Proceedings of the First International Joint e on Neural Networks, Washington, DC, pages 217–226, San Diego, 1989. IEEE, IEEE TAB Neural Network Committee.

    Google Scholar 

  7. T Kohonen. Self-Organization and Associative Memory. Springer, Berlin New York, 1984.

    Google Scholar 

  8. B. W. Mel. Murphy: A neurally-inspired connectionist approach to learning and performance in vision-based robot motion planning. Technical Report CCSR-89-17A, Center for Complex Systems Research Beckman Institute, University of Illinois, 1989.

    Google Scholar 

  9. K. Möller. Adaptive Roboterkontrolle mit konnektionistischen Systemen. Dissertation, Univ. Bonn, 1991.

    Google Scholar 

  10. K. Möller. Adaptive Roboterkontrolle mit konnektionistischen Systemen. infix-Verlag, St. Augustin, 1992.

    Google Scholar 

  11. K. Möller and S. Thrun. Task modularization by network modulation. In J. Rault, editor, Neuro-Nimes ’90, pages 419–432, 1990.

    Google Scholar 

  12. K. Möller and S. Thrun. Adaptive Roboterkontrolle. Wirtschaftsinformatik, 33(5),408–419, 1991.

    Google Scholar 

  13. D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning internal representations by error propagation. In D. E. Rumelhart and J. L. McClelland, editors, Parallel Distributed Processing. Vol. I + II. MIT Press, 1986.

    Google Scholar 

  14. H. Ritter and K. Schulten. Extending Kohonen’s self organizing mapping algorithm to learn ballistic movements. In R. Eckmiller and C. von der Malsburg, editors, Neural Computers, Springer-Verlag, Berlin, 1988.

    Google Scholar 

  15. H. Ritter, T. Martinez, and K. Schulten. Topology-conserving maps for learning visuo-motor-coordination. Neural Networks, 2(3):159–168, 1989.

    Article  Google Scholar 

  16. S. Thrun and K. Möller. On planning and exploration in non-discrete environments. Technical Report 528, GMD, St. Augustin, FRG, February, 1991.

    Google Scholar 

  17. A. H. Waibel. Modular construction of time-delay neural networks for speech recognition. Neural Computation, 1:39–46, 1989.

    Article  Google Scholar 

  18. P. J. Werbos. Beyond regression: New tools for prediction and analysis in the behavioral sciences. Unpublished PhD thesis, Harvard University, 1974.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institut für Informatik Abt. I, Universität Bonn, Römerstr. 164, D-5300, Bonn, Germany

    Knut Möller

Authors
  1. Knut Möller
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Fachbereich Informatik, Universität Koblenz/Landau, Rheinau 3-4, W-5400, Koblenz, Deutschland

    Ralf Hofestädt

  2. GMD-I1, GMD St. Augustin und Universität Bonn, Schloß Birlinghoven, W-5205, St. Augustin 1, Deutschland

    Fritz Krückeberg  & Thomas Lengauer  & 

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Möller, K. (1993). Das Lernen von mehrdeutigen Abbildungen mit fehlergesteuerter Zerlegung. In: Hofestädt, R., Krückeberg, F., Lengauer, T. (eds) Informatik in den Biowissenschaften. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-78072-1_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-78072-1_14

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-56456-0

  • Online ISBN: 978-3-642-78072-1

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation