A statistical method for structure learning of Bayesian networks from data
Soojung Ha, Seyun Kim, Minkook Suh, Hyunwoo Seong, Kwang Mo Jeong, Sung-Ho Kim · 2009
The Bayesian network, a powerful tool for predicting and diagnosing uncertain phenomena, is used in various fields including artificial intelligence, business administration, and medical science. We use a statistical approach, and present a simple algorithm for learning Bayesian network structure from data. First we obtain from data the original correlation graph and the correlation graphs when one or two variables are fixed. Then we construct a Bayesian network that would produce the most similar correlation graphs. Simulation results are given to demonstrate that the algorithm determines the network structure with a high accuracy.