Computer Science – Artificial Intelligence
Scientific paper
2012-04-07
(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 2, No. 7, pp 86-90, July 2011
Computer Science
Artificial Intelligence
6 pages
Scientific paper
Bayesian networks (BN) are used in a big range of applications but they have one issue concerning parameter learning. In real application, training data are always incomplete or some nodes are hidden. To deal with this problem many learning parameter algorithms are suggested foreground EM, Gibbs sampling and RBE algorithms. In order to limit the search space and escape from local maxima produced by executing EM algorithm, this paper presents a learning parameter algorithm that is a fusion of EM and RBE algorithms. This algorithm incorporates the range of a parameter into the EM algorithm. This range is calculated by the first step of RBE algorithm allowing a regularization of each parameter in bayesian network after the maximization step of the EM algorithm. The threshold EM algorithm is applied in brain tumor diagnosis and show some advantages and disadvantages over the EM algorithm.
kalti karim
Lamine Fradj Ben
Mahjoub Mohamed Ali
No associations
LandOfFree
The threshold EM algorithm for parameter learning in bayesian network with incomplete data does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with The threshold EM algorithm for parameter learning in bayesian network with incomplete data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The threshold EM algorithm for parameter learning in bayesian network with incomplete data will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-509058