Skip to main content
SpringerLink
Log in

Using mutual information to determine relevance in Bayesian networks

  • Bayesian Network
  • Conference paper
  • First Online:
PRICAI’98: Topics in Artificial Intelligence (PRICAI 1998)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1531))

Included in the following conference series:

Abstract

The control of Bayesian network (BN) evaluation is important in the development of real-time decision making systems. Techniques which focus attention by considering the relevance of variables in a BN allow more efficient use of computational resources. The statistical concept of mutual information (MI) between two related random variables can be used to measure relevance. We extend this idea to present a new measure of arc weights in a BN, and show how these can be combined to give a measure of the weight of a region of connected nodes. A heuristic path weight of a node or region relative to a specific query is also given. We present results from experiments which show that the MI weights are better than another measure based on the Bhattacharyya distance.

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. I. Beinlich, H. Suermondt, R. Chavez, and G. Cooper. The alarm monitoring system: A case study with two probabilistic inference techniques for belief networks. In Proc. of the 2nd European Conf. on Artificial Intelligence in medicine, pages 689–693, 1992.

    Google Scholar 

  2. A. Bhattacharyya. On a measure of divergence between two statistical populations defined by their probability distributions. Bulletin of the Calcutta Mathematics Society, 35:99–110, 1943.

    MATH  MathSciNet  Google Scholar 

  3. B. Boerlage. Link strengths in Bayesian networks. Master’s thesis, Dept. of Computer Science, U. of British Columbia, 1995.

    Google Scholar 

  4. John Brown. Hailfinder: Bayesian system that combines meteorological data and models with expert judgment to forecast severe summer weather in ne colorado. INFORMS Atlanta, November 3–6, 1996. Talk. See http://www.informs.org/Conf/ATL96/TALKS/SD12.html, 1996.

    Google Scholar 

  5. Paul R. Cohen. Empirical Methods for Artificial Intelligence. MIT Press, Cambridge, Massachusetts, 1995.

    MATH  Google Scholar 

  6. G.F. Cooper. The computational complexity of probabilistic inference using bayesian belief networks. Artificial Intelligence, 42:393–405, 1990.

    Article  MATH  MathSciNet  Google Scholar 

  7. P. Dagum and M. Luby. Approximating probabilistic inference in belief networks is NP-hard. Artificial Intelligence, pages 141–153, 1993.

    Google Scholar 

  8. Denise Draper. Localized Partial Evaluation of Belief Networks. PhD thesis, Dept. of Computer Science, University of Washington, 1995.

    Google Scholar 

  9. N. Jitnah and A. Nicholson. A. best-first search method for anytime evaluation of belief networks. In ICONIP’97: International Conference on Neural Information Processing (ICONIP’97), pages 600–603, 1997.

    Google Scholar 

  10. N. Jitnah and A. Nicholson. treenets: A framework for anytime evaluation of belief networks. In First International Joint Conference on Qualitative and Quantitative Practical Reasoning, ECSQARU-FAPR’97, 1997. Lecture notes in Artificial Intelligence, Springer-Verlag.

    Google Scholar 

  11. S.L. Lauritzen and D.J. Spiegelhalter. Local computations with probabilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society, 50(2):157–224, 1988.

    MATH  MathSciNet  Google Scholar 

  12. C. Liu and M. Wellman. On state-space abstraction for anytime evaluation of bayesian networks. In IJCAI 95: Anytime Algorithms and Deliberation Scheduling Workshop, pages 91–98, 1995.

    Google Scholar 

  13. Judea Pearl, Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo, Ca., 1988.

    MATH  Google Scholar 

  14. K. L. Poh and E. Horvitz. A graph-theoretic analysis of information value. In Proceedings of the Twelfth Conference on Uncertainty in AI, pages 427–435, 1996.

    Google Scholar 

  15. C. E. Shannon and W. Weaver. The mathematical theory of communication. University of Illinois Press, 1949.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Software Engineering, Monash University, 3168, Clayton, VIC, Australia

    A. E. Nicholson & N. Jitnah

Authors
  1. A. E. Nicholson
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. N. Jitnah
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Hing-Yan Lee Hiroshi Motoda

Rights and permissions

Reprints and permissions

Copyright information

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Nicholson, A.E., Jitnah, N. (1998). Using mutual information to determine relevance in Bayesian networks. In: Lee, HY., Motoda, H. (eds) PRICAI’98: Topics in Artificial Intelligence. PRICAI 1998. Lecture Notes in Computer Science, vol 1531. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0095287

Download citation

  • DOI: https://doi.org/10.1007/BFb0095287

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-65271-7

  • Online ISBN: 978-3-540-49461-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation