Skip to main content
SpringerLink
Log in

Structure-Based Categorisation of Bayesian Network Parameters

  • Conference paper
  • First Online:
Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU 2017)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10369))

  • 578 Accesses

Abstract

Bayesian networks typically require thousands of probability para-meters for their specification, many of which are bound to be inaccurate. Know-ledge of the direction of change in an output probability of a network occasioned by changes in one or more of its parameters, i.e. the qualitative effect of parameter changes, has been shown to be useful both for parameter tuning and in pre-processing for inference in credal networks. In this paper we identify classes of parameter for which the qualitative effect on a given output of interest can be identified based upon graphical considerations.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and 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

Notes

  1. 1.

    Note that the parameters of the local distributions that are in \(\mathscr {B}\) but not in \({\mathscr {B}}_q\) do not affect the output of interest in any way.

References

  1. Bolt, J.H., De Bock, J., Renooij, S.: Exploiting Bayesian network sensitivity functions for inference in credal networks. In: Proceedings of the 22nd European Conference on Artificial Intelligence, vol. 285, pp. 646–654 (2016)

    Google Scholar 

  2. Bolt, J.H., van der Gaag, L.C.: Balanced sensitivity functions for tuning multi-dimensional Bayesian network classifiers. Int. J. Approx. Reason. 80c, 361–376 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  3. Coupé, V.M.H., van der Gaag, L.C.: Properties of sensitivity analysis of Bayesian belief networks. Ann. Math. Artif. Intell. 36(4), 323–356 (2002)

    Article  MathSciNet  MATH  Google Scholar 

  4. van der Gaag, L.C.: On evidence absorption for belief networks. Int. J. Approx. Reason. 15(3), 265–286 (1996)

    Article  MathSciNet  MATH  Google Scholar 

  5. Jensen, F.V., Nielsen, T.D.: Bayesian Networks and Decision Graphs, 2nd edn. Springer, New York (2007)

    Book  MATH  Google Scholar 

  6. Kjærulff, U., van der Gaag, L.C.: Making sensitivity analysis computationally efficient. In: Boutilier, C., Goldszmidt, M. (eds.) Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, pp. 317–325. Morgan Kaufmann Publishers, San Francisco (2000)

    Google Scholar 

  7. Meekes, M., Renooij, S., Gaag, L.C.: Relevance of evidence in Bayesian networks. In: Destercke, S., Denoeux, T. (eds.) ECSQARU 2015. LNCS, vol. 9161, pp. 366–375. Springer, Cham (2015). doi:10.1007/978-3-319-20807-7_33

    Chapter  Google Scholar 

  8. Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers, Palo Alto (1988)

    MATH  Google Scholar 

  9. Renooij, S.: Co-variation for sensitivity analysis in Bayesian networks: properties, consequences and alternatives. Int. J. Approx. Reason. 55, 1022–1042 (2014)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

This research was supported by the Netherlands Organisation for Scientific Research (NWO).

Author information

Authors and Affiliations

  1. Department of Information and Computing Sciences, Utrecht University, P.O. Box 80.089, 3508 TB, Utrecht, The Netherlands

    Janneke H. Bolt & Silja Renooij

Authors
  1. Janneke H. Bolt
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Silja Renooij
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Janneke H. Bolt .

Editor information

Editors and Affiliations

  1. IDSIA, Lugano, Switzerland

    Alessandro Antonucci

  2. ONERA, Toulouse, France

    Laurence Cholvy

  3. Aix-Marseille University, Marseille, France

    Odile Papini

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Bolt, J.H., Renooij, S. (2017). Structure-Based Categorisation of Bayesian Network Parameters. In: Antonucci, A., Cholvy, L., Papini, O. (eds) Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2017. Lecture Notes in Computer Science(), vol 10369. Springer, Cham. https://doi.org/10.1007/978-3-319-61581-3_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-61581-3_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-61580-6

  • Online ISBN: 978-3-319-61581-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation