Bayesian network Exploitation of probabilistic reasoning and statistical learning
What is Bayesian network?
Bayesian network is a directed graph, and is a probabilistic model which consists of 3 kinds of components. Those are the following:
 Nodes representing probability variables
 Arcs representing conditional dependency relations among the variables
 Conditional probability of those relations
Bayesian networks are used for modelling knowledge in very large domains, for example, gene regulatory networks, medicine, engineering, text analysis, image processing, decision support systems, prospective study, data base exploitation with machine learning, etc.
The Bayesian Network approach merges and supersedes existing approaches coming from Artificial Intelligence and Data Mining, both symbolic and statistical ones. Bayesian Networks are rigorously justified, provide a distributed knowledge representation, and are as understandable as a rule base. They deal particularly well with uncertainty, and they can be manually generated by consultation of an expert, or inductively built by machine learning.
(source: web page of BAYESIA S.A. )
