Learning from Multiple Bayesian Networks for the Revision and Refinement of Expert Systems

  • Michael Borth
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2479)


Many expert systems for diagnosis, prediction, and analysis in complex dynamic scenarios use Bayesian networks for reasoning under uncertainty. These networks often benefit from adaptations to their specific conditions by machine learning on operational data. The knowledge encoded in these adapted networks yields insights as to typical modes of operations, configurations, types of usage, etc. To utilize this knowledge for the revision and refinement of existing and future expert systems, we developed a contextsensitive machine learning process that uses a multitude of Bayesian networks as input for concept discovery. Our algorithms allow the identification of typical network fragments, their relations, and the context in which they are valid. With these results, we are able to substitute parts of existing networks that are not yet optimally adapted to their tasks and initiate a knowledge engineering process aiming at a precise network generation for future expert systems which accounts for previously unknown characteristics.


Bayesian Network Association Rule Knowledge Discovery Application Scenario Concept Discovery 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    F. Jensen, Bayesian Networks and Decision Graphs, Springer, 2001.Google Scholar
  2. 2.
    D. Heckerman, M. Wellman: Real World Applications of Bayesian Networks, in Communications of the ACM, 1995.Google Scholar
  3. 3.
    D. Heckerman, A tutorial on learning with Bayesian Networks, Microsoft Research Report No MSR-TR-95-06, 1995.Google Scholar
  4. 4.
    M. Borth: Die Erstellung von Bayes-Netzen zur Diagnose Technischer Systeme, Thesis, University of Ulm, Germany, 1999 (in German).Google Scholar
  5. 5.
    D. Koller, A. Pfeffer: Object-oriented Bayesian Networks, In Proc. of the 13 th Conf. on Uncertainty in Artificial Intelligence, 1997.Google Scholar
  6. 6.
    H. Kargupta, P. Chan (eds.): Advances in Distributed and Parallel Knowledge Discovery, AAAI Press, 2000.Google Scholar
  7. 7.
    F. Provost: Distributed Data Mining: Scaling up and Beyond. In H. Kargupta, P. Chan (eds.): Advances in Distributed and Parallel Knowledge Discovery, AAAI Press, 2000.Google Scholar
  8. 8.
    R. Wirth, M. Borth, J. Hipp: When Distribution is Part of the Semantics. In Proc. of the PKDD 2001 Workshop on Ubiquitous Data Mining for Mobile and Distributed Environments, 2001.Google Scholar
  9. 9.
    J. Pearl: Causality, Cambridge University Press, 2000.Google Scholar
  10. 10.
    K. Thompson, P. Langley: Concept Formation in Structured Domains, in Concept Formation, Morgan Kaufmann, 1991.Google Scholar
  11. 11.
    J. Quinlan: Learning logical definitions from relations. Machine Learning (5) p. 239–266, 1990.Google Scholar
  12. 12.
    K. Laskey, S. Mahoney: Network Fragments: Representing Knowledge for Construction Probabilistic Models Networks, in Proc. of the 13 th Conf. on Uncertainty in Artificial Intelligence, 1997.Google Scholar
  13. 13.
    J. Gennari, P. Langley, D. Fisher: Models of incremental concept formation. Artificial Intelligence (40) p. 11–61, 1989.Google Scholar
  14. 14.
    R. Agrawal, T. Imielinski, A. Swami: Mining association rules between sets of items in large databases. In Proc. of the ACM SIGMOD’ 93, 1993.Google Scholar
  15. 15.
    J. Hipp, U. Güntzer, G. Nakhaeizadeh: Algorithms for Association Rule Mining-A General Survey and Comparison. SIGKDD Explorations 2(1), 2000.Google Scholar
  16. 16.
    M. Gluck, J. Corter: Information, uncertainty and the utility of categories. In Proc. of the 7th Annual Conf. of the Cognitive Science Society, 1985.Google Scholar
  17. 17.
    D. Fisher: Iterative Optimization and Simplification of Hierarchical Clusterings, JAIR, vol 4 p. 147–179, 1996.zbMATHGoogle Scholar
  18. 18.
    H. Ellis: Human Learning and Cognition, 1972Google Scholar
  19. 19.
    I. Beinlich, H. J. Suermondt, R. M. Chavez, G. F. Cooper: The ALARM monitoring system. In Proc. of the 2nd European Conf. on Artificial Intelligence in Medicine, 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Michael Borth
    • 1
  1. 1.DaimlerChrysler Research and Technology RIC/AMUlmF.R. Germany

Personalised recommendations