BNC Structure Learning: G2 Algorithm based Heuristic
Zekai Cheng, Feng Qin, Bo Yang · 2006
Structure learning for Bayesian networks classifier is NP-hard problem, K2 algorithm is one of efficacious and accurate algorithm. K2 algorithm confirms the order of nodes firstly. To a certain extent this limits in non-information. This paper purposes a new heuristic Bayesian networks classifier structure learning G2 algorithm. G2 algorithm use NB and TAN structure which learns as heuristic information, using K2 algorithm learning BNC structure. The experimental result shows that G2 algorithm can solve nodes order in non-information. Arcs are sententious, compare NB and TAN structure, it's more reasonable, classification accuracy improves, this algorithm adapts many aspects