Skip to main content
SpringerLink
Log in

Training neural networks with influence diagrams

  • Conference paper
  • First Online:
Progress in Evolutionary Computation (EvoWorkshops 1993, EvoWorkshops 1994)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 956))

  • 162 Accesses

Abstract

This paper discusses the application of Influence Diagrams on training Neural Networks. The basic concepts of these two methodologies are presented as a brief review. The conventional back-propagation training procedure is compared to other alternatives, by means of an example on visual pattern recognition.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Davalo, E. & NaÏm, P. Des Réseaux de Neurones. Eurolles, Paris, 1990.

    Google Scholar 

  2. Henrion, Max, Breese, J. S. & Horvitz, E. Decision Analysis and Expert Systems. AI Magazine, Winter 91.

    Google Scholar 

  3. Hertz, Jonh A., Krogh, A. & Palmer, R. Introduction to the Theory of Neural Computation. Addison-Wesley, Redwood City, 1991.

    Google Scholar 

  4. Lauritzen, S. L. & Spiegelhalter, D. J. Local Computations with Probabilities on Graphical Structures and Their Application to Expert Systems. Journal Royal Statistical Society, 50, 1988.

    Google Scholar 

  5. Machado, A. C. & Campos, M. M. On The Application of Influence Diagrams to Pattern Recognition Problems. Proceedings of the Workshop on Cybernetic Vision, SÃo Carlos, 1994.

    Google Scholar 

  6. Pearl, J. Fusion, Propagation and Structuring in Belief Networks. Artificial Intelligence, 29, 1986.

    Google Scholar 

  7. Pearl, J. Distributed Revision of Composite Beliefs. Artificial Intelligence, 33, 1987.

    Google Scholar 

  8. Rumelhart, D., Hinton, G. & Williams R. Parallel Distributed Processing: Explorations in the Microstructures of Cognition. MIT Press, Cambridge, 1986.

    Google Scholar 

  9. Suermondt, H. J. & Cooper, G. F. Updating Probabilities in Multiply-Connected Belief Networks. Proceedings of the 4th Workshop on Uncertainty in Artificial Intelligence, Minneapolis, 1988.

    Google Scholar 

  10. Thomas, J. B. Introduction to Probability. Springer-Verlag, New York, 1986.

    Google Scholar 

  11. Tou, J. T. & Gonzalez, R. Pattern Recognition Principles. Reading, 1974.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. DCC-ICEx, Universidade Federal de Minas Gerais, Caixa Postal 702, CEP 30.161-970, Belo Horizonte-MG, Brazil

    Alexei Manso CorrÊa Machado & Mário Fernando Montenegro Campos

Authors
  1. Alexei Manso CorrÊa Machado
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mário Fernando Montenegro Campos
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Xin Yao

Rights and permissions

Reprints and permissions

Copyright information

© 1995 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Machado, A.M.C., Campos, M.F.M. (1995). Training neural networks with influence diagrams. In: Yao, X. (eds) Progress in Evolutionary Computation. EvoWorkshops EvoWorkshops 1993 1994. Lecture Notes in Computer Science, vol 956. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60154-6_59

Download citation

  • DOI: https://doi.org/10.1007/3-540-60154-6_59

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-60154-8

  • Online ISBN: 978-3-540-49528-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation