A Bayesian inference network, also called a Bayesian network, is a directed acyclic graph that models random variables as nodes and their conditional dependencies as edges.
It uses Bayesian probability theory to quantify uncertainties and update probabilities when new information becomes available.
Each node has a conditional probability distribution that indicates how likely the node is, given its parent nodes.
The network allows efficient inference through algorithms such as variable elimination or belief propagation.
Bayesian inference networks are used in areas such as diagnosis, prognosis, and decision support.