Structure Learning of Bayesian Networks by Hybrid Genetic Algorithms

  • Pedro Larrañaga
  • Roberto Murga
  • Mikel Poza
  • Cindy Kuijpers
Part of the Lecture Notes in Statistics book series (LNS, volume 112)


This paper demonstrates how genetic algorithms can be used to discover the structure of a Bayesian network from a given database with cases. The results presented, were obtained by applying four different types of genetic algorithms — SSGA (Steady State Genetic Algorithm), GAeλ (Genetic Algorithm elistist of degree λ), hSSGA (hybrid Steady State Genetic Algorithm) and the hGAeλ (hybrid Genetic Algorithm elitist of degree λ) — to simulations of the ALARM Network. The behaviour of these algorithms is studied as their parameters are varied.


Genetic Algorithm Bayesian Network Mutation Operator Hybrid Algorithm Parent Node 
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. [Beinlich89]
    Beinlich, I.A., Suermondt, H.J., Chavez, R.M., & Cooper, G.F. (1989). The ALARM monitoring system: A case study with two probabilistic inferences techniques for belief networks. Proceedings of the Second European Conference on Artificial Intelligence in Medicine (pp. 247–256 ).Google Scholar
  2. [Bouckaert93]
    Bouckaert, R.R. (1993). Probabilistic network construction using the minimum description length principle. In M. Clarke, R. Kruse & S. Moral (Eds.) Symbolic and Quantitative Approaches to Reasoning and Uncertainty — ECSQARU-93, No. 747, Lectures Notes in Computing Science, pp. 41–48, Springer-Verlag.Google Scholar
  3. [Bouckaert94]
    Bouckaert, R.R. (1994). Properties of Bayesian belief network learning algorithms. Uncertainty in Artificial Intelligence, Tenth Annual Conference (pp. 102–109 ). San Francisco, CA: Morgan Kaufmann.Google Scholar
  4. [Chakraborty93]
    Chakraborty, U.K., & Dastidar, D.G. (1993). Using reliability analysis to estimate the number of generations to convergence in genetic algorithms. Information Processing Letters, 46, 199–209.MathSciNetzbMATHCrossRefGoogle Scholar
  5. [Chickering95]
    Chickering, D.M., Geiger, D., & Heckerman, D. (1995). Learning Bayesian networks: Search methods and experimental results. Preliminary Papers of the Fifth International Workshop on Artificial Intelligence and Statistics (pp. 112–128 ).Google Scholar
  6. [Chow68]
    Chow, C.K., & Liu, C.N. (1968). Approximating discrete probability distributions with dependence trees. IEEE Transactions on Information Theory, 14, 462–467.zbMATHCrossRefGoogle Scholar
  7. [Cooper92]
    Cooper, G.F., & Herskovits, E.H. (1992). A Bayesian method for the induction of probabilistic networks from data. Machine Learning, 9, 309–347.zbMATHGoogle Scholar
  8. [Davis9l]
    Davis, L. (Ed.) (1991). Handbook of Genetic Algorithms. New York: Van Nostrand Reinhold.Google Scholar
  9. [Eiben90]
    Eiben, A.E., Aarts, E.H.L., & Van Hee, K.M. (1990). Global convergence of genetic algorithms: An infinite Markov chain analysis. Computing Science Notes, Eindhoven University of Technology, The Netherlands.Google Scholar
  10. [Fogel62]
    Fogel, L.J. (1962). Atonomous automata. Ind. Res, 4, 14–19.Google Scholar
  11. [Fung90]
    Fung, R.M., & Crawford, S.L. (1990). CONSTRUCTOR: A system for the induction of probabilistic models. Proceedings of AAAI (pp. 762–769).Google Scholar
  12. [Goldberg89]
    Goldberg, D.E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Reading, MA: Addison-Wesley.zbMATHGoogle Scholar
  13. [Henrion88]
    Henrion, M. (1988). Propagating uncertainty in Bayesian networks by probabilistic logic sampling. In J. Lemmer & L. Kanal (Eds.) Uncertainty in Artificial Intelligence, 2, pp. 149–163, North-Holland.Google Scholar
  14. [Herskovits9l]
    Herskovits, E. H. (1991). Computer based probabilistic-network construction. Doctoral dissertation, Medical Information Sciences, Stanford University.Google Scholar
  15. [Herskovits90]
    Herskovits, E. H., & Cooper, G.F. (1990). Kutatô: An entropy-driven system for construction of probabilistic expert systems from databases Report KSL-9022, Knowledge Systems Laboratory, Medical Computer Science, Stanford University.Google Scholar
  16. [Holland75]
    Holland, J.H. (1975). Adaptation in Natural and Artificial Systems. The University of Michigan Press.Google Scholar
  17. [Lauritzen93]
    Lauritzen, S.L., Thiesson, B., & Spiegelhalter, D.J. (1993). Diagnostic systems created by model selection methods-A case study. Fourth International Workshop on Artificial Intelligence and Statistics (pp. 93–105 ).Google Scholar
  18. [Pear188]
    Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems. San Mateo, CA: Morgan Kaufmann.Google Scholar
  19. [Rebane89]
    Rebane, G., & Pearl, J. (1989). The recovery of causal polytrees from statistical data. In L. Kanal, T. Levitt & J. Lemmer (Eds.) Uncertainty in Artificial Intelligence, 3, pp. 175–182, North-Holland.Google Scholar
  20. [Rudolph94]
    Rudolph, G. (1994). Convergence analysis of canonical genetic algoritms. IEEE Transactions on Neural Networks, vol. 5, no. 1, 96–101.CrossRefGoogle Scholar
  21. [Schwefel67]
    Schwefel, H.-P. (1967). Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie. Basel: Birkhäuser.Google Scholar
  22. [Wedelin93]
    Wedelin, D. (1993). Efficient algorithms for probabilistic inference combinatorial optimization and the discovery of causal structure from data. Doctoral dissertation, Chalmers University of Technology, Göteborg.Google Scholar

Copyright information

© Springer-Verlag New York, Inc. 1996

Authors and Affiliations

  • Pedro Larrañaga
    • 1
  • Roberto Murga
    • 1
  • Mikel Poza
    • 1
  • Cindy Kuijpers
    • 1
  1. 1.Department of Computer Science and Artificial IntelligenceUniversity of the Basque CountrySan SebastiánSpain

Personalised recommendations