BayesiaLab is a comprehensive tool for creating and utilizing Bayesian networks. With BayesiaLab, you can define, learn, edit, and analyze Bayesian network models.

The BayesiaLab User Guide describes the functionalities and the user interface of BayesiaLab.

While BayesiaLab is running, you can always press to bring up the help files. Alternatively, pressing displays the contextual help cursor. Once it's active, you can click on any component, including menus and submenus, to display the context-specific help pages. |

Bayesian networks are graphical structures, consisting of nodes and arcs. Nodes represent random variables, arcs represent direct probabilistic relationships between the connected nodes/variables. These probabilistic relationships are quantified by probability distributions. Such probability distributions are recorded in conditional probability tables that are associated with each node.

Bayesian networks can be machine-learned from data or, alternatively, they can be manually modeled by domain experts. Once a Bayesian network is created, it can be used for updating the probability distribution of each variable, given any evidence set on other variables in the network.