Abstract
We consider approximate inference in hybrid Bayesian Networks (BNs) and present a new iterative algorithm that efficiently combines dynamic discretization with robust propagation algorithms on junction trees. Our approach offers a significant extension to Bayesian Network theory and practice by offering a flexible way of modeling continuous nodes in BNs conditioned on complex configurations of evidence and intermixed with discrete nodes as both parents and children of continuous nodes. Our algorithm is implemented in a commercial Bayesian Network software package, AgenaRisk, which allows model construction and testing to be carried out easily. The results from the empirical trials clearly show how our software can deal effectively with different type of hybrid models containing elements of expert judgment as well as statistical inference. In particular, we show how the rapid convergence of the algorithm towards zones of high probability density, make robust inference analysis possible even in situations where, due to the lack of information in both prior and data, robust sampling becomes unfeasible.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Agena Ltd. AgenaRisk software package. www.agenarisk.com (2005)
Bernardo, J., Smith, A.: Bayesian Theory. Wiley, New York (1994)
Brigham, E.: Fast Fourier Transform and Its Applications, 1st edn. Prentice Hall, New York (1988)
Buntine, W.: Operations for learning with graphical models. Artif. Intell. 2, 159–225 (1994)
Casella, G., George, E.I.: Explaining the Gibbs sampler. Am. Stat. 46, 167–174 (1992)
Cobb, B., Shenoy, P.: Inference in hybrid Bayesian networks with mixtures of truncated exponentials. University of Kansas School of Business, working paper 294 (2005a)
Cobb, B., Shenoy, P.: Nonlinear deterministic relationships in Bayesian networks. In: Godo, L. (Ed.) ECSQARU, pp. 27–38. Springer, Berlin (2005b)
Dobson, A.J.: An Introduction to Generalized Linear Models. Chapman & Hall, New York (1990)
Fenton, N., Krause, P., Neil, M.: Probabilistic modeling for software quality control. J. Appl. Non-Classical Log. 12(2), 173–188 (2002)
Fenton, N., Marsh, W., Neil, M., Cates, P., Forey, S., Tailor, T.: Making resource decisions for software projects. In: 26th International Conference on Software Engineering, Edinburgh, United Kingdom (2004)
Gelman, A., Carlin, J.B., Stern, H.S., Rubin, D.B.: Bayesian Data Analysis, 2nd edn., pp. 209–302. Chapman and Hall, New York (2004)
Gilks, W.R., Richardson, S., Spiegelhalter, D.J.: Markov Chain Monte Carlo in Practice. Chapman and Hall, London (1996)
Heckerman, D., Mamdani, A., Wellman, M.P.: Real-world applications’ of Bayesian networks. Commun. ACM 38(3), 24–68 (1995)
Huang, C., Darwiche, A.: Inference in belief networks: A procedural guide. Int. J. Approx. Reason. 15(3), 225–263 (1996)
Hugin: www.hugin.com (2005)
Jensen, F.: An Introduction to Bayesian Networks. Springer, Berlin (1996)
Jensen, F., Lauritzen, S.L., Olesen, K.: Bayesian updating in recursive graphical models by local computations. Comput. Stat. Quart. 4, 260–282 (1990)
Koller, D., Lerner, U., Angelov, D.: A general algorithm for approximate inference and its applications to hybrid Bayes nets. In: Laskey, K.B., Prade, H. (eds.) Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence, pp. 324–333 (1999)
Kozlov, A.V., Koller, D.: Nonuniform dynamic discretization in hybrid networks. In: Geiger, D., Shenoy, P.P. (eds.) Uncertain. Artif. Intell. 13, 314–325 (1997)
Lauritzen, S.L.: Graphical Models, Oxford (1996)
Lauritzen, S.L., Jensen, F.: Stable local computation with conditional Gaussian distributions. Stat. Comput. 11, 191–203 (2001)
Lauritzen, S.L., Spiegelhalter, D.J.: Local computations with probabilities on graphical structures and their application to expert systems (with discussion). J. Roy. Stat. Soc. Ser. B 50(2), 157–224 (1988)
Moral, S., Rumı, R., Salmeron, A., Mixtures of truncated exponentials in hybrid Bayesian networks. In: Besnard, P., Benferhart, S. (eds.) Symbolic and Quantitative Approaches to Reasoning under Uncertainty. Lecture Notes in Artificial Intelligence, vol. 2143, pp. 156–167 (2001)
Murphy, K.: A variational approximation for Bayesian networks with discrete and continuous latent variables. In: Laskey, K.B., Prade, H. (eds.) Uncertainty in Artificial Intelligence, vol. 15, pp. 467–475 (1999)
Netica: www.norsys.com (2005)
Neil, M., Fenton, N., Forey, S., Harris, R.: Using Bayesian belief networks to predict the reliability of military vehicles. IEE Comput. Control Eng. J. 12(1), 11–20 (2001)
Neil, M., Malcolm, B., Shaw, R.: Modelling an air traffic control environment using Bayesian belief networks. In: 21st International System Safety Conference, Ottawa, ON, Canada (2003a)
Neil, M., Krause, P., Fenton, N.: Software quality prediction using Bayesian networks in software engineering with computational intelligence. In: (ed.) Khoshgoftaar, T.M. The Kluwer International Series in Engineering and Computer Science, vol. 73 (2003b)
Pearl, J.: Fusion, propogation and structuring in belief networks. Artif. Intell. 29, 241–288 (1986)
Pearl, J.: Graphical models, causality, and intervention. Stat. Sci. 8(3), 266–273 (1993)
Spiegelhalter, D.J., Thomas, A., Best, N.G., Gilks, W.R.: BUGS: Bayesian inference using Gibbs sampling, Version 0.50. MRC Biostatistics Unit, Cambridge (1995)
Spiegelhalter, D.J., Lauritzen, S.L.: Sequential updating of conditional probabilities on directed graphical structures. Networks 20, 579–605 (1990)
Shacter, R., Peot, M.: 1989. Simulation approaches to general probabilistic inference on belief networks. In: Proceedings of the 5th Annual Conference on Uncertainty in AI (UAI), pp. 221–230
Shenoy, P.: Binary join trees for computing marginals in the Shenoy–Shafer architecture. Int. J. Approx. Reason. 17(1), 1–25 (1997)
Shenoy, P., Shafer, G.: Axioms for Probability and Belief-Function Propagation, Readings in Uncertain Reasoning, pp. 575–610. Kaufmann, Los Altos (1990)
Whittaker, J.: Graphical Models in Applied Multivariate Statistics. Wiley, New York (1990)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Neil, M., Tailor, M. & Marquez, D. Inference in hybrid Bayesian networks using dynamic discretization. Stat Comput 17, 219–233 (2007). https://doi.org/10.1007/s11222-007-9018-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-007-9018-y