Abstract
This paper presents new idea for Markov blanket approximation. It uses well known heuristic ordering of variables based on mutual information, but in another way then it was considered in previous works. Instead of using it as a simple help tool in a more complicated method most often based on statistical tests - presented here idea tries to rely without any further statistical tests only on the heuristic and its previously not considered interesting properties.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Koller, D., Sahami, M.: Toward Optimal Feature Selection, Technical Report. Stanford InfoLab (1996)
Margaritis, D., Thrun, S.: Bayesian Network Induction via Local Neighborhoods. In: Proceedings of the Neural Information Processing Systems, pp. 505–511 (1999)
Neapolitan, R.: Learning Bayesian Networks. Prentice Hall, Upper Saddle River (2004)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Francisco (1988)
Tsamardinos, I., Aliferis, C., Statnikov, A.: Algorithms for Large Scale Markov Blanket Discovery. In: Proceedings of the FLAIRS (2003)
Tsamardinos, I., Brown, L., Aliferis, C.: The Max-Min Hill-Climbing Bayesian Network Structure Learning Algorithm. Machine Learning 65(1), 31–78 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Betliński, P. (2011). Markov Blanket Approximation Based on Clustering. In: Kryszkiewicz, M., Rybinski, H., Skowron, A., Raś, Z.W. (eds) Foundations of Intelligent Systems. ISMIS 2011. Lecture Notes in Computer Science(), vol 6804. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21916-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-21916-0_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21915-3
Online ISBN: 978-3-642-21916-0
eBook Packages: Computer ScienceComputer Science (R0)