Skip to main content
SpringerLink
Log in
Book cover

International Workshop on Artificial Neural Networks

IWANN 1993: New Trends in Neural Computation pp 519–524Cite as

Rejection of incorrect answers from a neural net classifier

  • Conference paper
  • First Online:

  • 291 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 686))

Abstract

The notion of approximator rejection is described, and applied to a neural network. For a real world classification problem the residual error is shown to decrease with the inverse exponential of the fraction of patterns rejected. The trade-off of “good” patterns rejected and “bad” patterns rejected is shown to increase approximately linearly with rejection rate. A compromise is therefore necessary between trade-off/rejection rate and residual error. A meta-level solution is proposed for removal of the residual error, through use of a modular system of parallel approximators.

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. U. Beyer and F. J. Śmieja. Quantitative aspects of data-driven information processing. Technical Report #812, Gesellschaft für Mathematik und Datenverarbeitung, St Augustin, Germany, March 1993.

    Google Scholar 

  2. S. Hubrig-Schaumburg. Handwritten character recognition using a reflective modular neural network system. Master's thesis, Bonn University, Germany, 1992.

    Google Scholar 

  3. R. P. Lippmann. An introduction to computing with neural nets. IEEE ASSP Magazine, April 1987.

    Google Scholar 

  4. H. Mühlenbein. Editorial. Parallel Computing, 14(3):247–248, August 1990. special edition on neural networks.

    Google Scholar 

  5. D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning internal representations by error propagation. Nature, 323(533), 1986.

    Google Scholar 

  6. O. G. Selfridge. Pandemonium: a paradigm for learning. In The Mechanisation of Thought Processes: Proceedings of a Symposium Held at the National Physical Laboratory, November 1958, pages 511–527, London: HMSO, 1958.

    Google Scholar 

  7. F. J. Śmieja. Neural network constructive algorithms: Trading generalization for learning efficiency? Circuits, Systems and Signal Processing, 12(2):331–374, 1993.

    Google Scholar 

  8. F. J. Śmieja and H. Mühlenbein. The geometry of multilayer perceptron solutions. Parallel Computing, 14:261–275, 1990.

    Google Scholar 

  9. F. J. Śmieja and H. Mühlenbein. Reflective modular neural network systems. Technical Report #633, GMD, Sankt Augustin, Germany, February 1992.

    Google Scholar 

  10. F. Weber. Self-reflective exploration of the kinematics of a two-joint robot arm. Diplomarbeit, University of Bonn, Germany, 1992. in German.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. German National Research Centre for Computer Science (GMD), Schloß Birlinghoven, 5205, St. Augustin 1, Germany

    F. J. Śmieja

Authors
  1. F. J. Śmieja
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

José Mira Joan Cabestany Alberto Prieto

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Śmieja, F.J. (1993). Rejection of incorrect answers from a neural net classifier. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_196

Download citation

  • DOI: https://doi.org/10.1007/3-540-56798-4_196

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-56798-1

  • Online ISBN: 978-3-540-47741-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation