The threshold EM algorithm for parameter learning in bayesian network with incomplete data
作者： Fradj Ben Lamine , Karim Kalti , Mohamed Ali Mahjoub
DOI:
关键词:
摘要: Bayesian networks (BN) are used in a big range of applications but they have one issue concerning parameter learning. In real application, training data always incomplete or some nodes hidden. To deal with this problem many learning algorithms suggested foreground EM, Gibbs sampling and RBE algorithms. order to limit the search space escape from local maxima produced by executing EM algorithm, paper presents algorithm that is fusion This incorporates into algorithm. calculated first step allowing regularization each bayesian network after maximization The threshold applied brain tumor diagnosis show advantages disadvantages over
harvard.edu
arxiv.org参考文章(12)
Basilio Sierra, Iñaki Inza, Pedro Larrañaga, Medical Bayes Networks ISMDA '00 Proceedings of the First International Symposium on Medical Data Analysis. pp. 4- 14 ,(2000) , 10.1007/3-540-39949-6_2
Marco Ramoni, Paola Sebastiani, Robust Learning with Missing Data Machine Learning. ,vol. 45, pp. 147- 170 ,(2001) , 10.1023/A:1010968702992
Mohamed Ali Mahjoub, Karim Kalti, Software Comparison Dealing with Bayesian Networks Advances in Neural Networks – ISNN 2011. pp. 168- 177 ,(2011) , 10.1007/978-3-642-21111-9_19
Luis M de Campos, Juan M Fernández-Luna, Juan F Huete, Bayesian networks and information retrieval: an introduction to the special issue Information Processing and Management. ,vol. 40, pp. 727- 733 ,(2004) , 10.1016/J.IPM.2004.03.001
Sebastiani Paola, Sebastiani Paola, Ramoni Marco, Bayesian Inference with Missing Data Using Bound and Collapse Journal of Computational and Graphical Statistics. ,vol. 9, pp. 779- 800 ,(2000) , 10.1080/10618600.2000.10474913
Stuart Geman, Donald Geman, Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-6, pp. 721- 741 ,(1984) , 10.1109/TPAMI.1984.4767596
A. P. Dempster, N. M. Laird, D. B. Rubin, Maximum Likelihood from Incomplete Data Via theEMAlgorithm Journal of the Royal Statistical Society: Series B (Methodological). ,vol. 39, pp. 1- 22 ,(1977) , 10.1111/J.2517-6161.1977.TB01600.X
José M Pena, Johan Björkegren, Jesper Tegnér, Growing Bayesian network models of gene networks from seed genes Bioinformatics. ,vol. 21, pp. 224- 229 ,(2005) , 10.1093/BIOINFORMATICS/BTI1137
Khlifia Jayech, Mohamed Ali Mahjoub, New approach using Bayesian Network to improve content based image classification systems arXiv: Computer Vision and Pattern Recognition. ,(2012)
Steffen L. Lauritzen, The EM algorithm for graphical association models with missing data Computational Statistics & Data Analysis. ,vol. 19, pp. 191- 201 ,(1995) , 10.1016/0167-9473(93)E0056-A