Conventional Bayesian Belief Network (BBN)

The conventional Bayesian Belief Network (BBN) is a probabilistic graphical model that defines the structural dependency among the random variables by graphical means.

 A BBN has the following elements:

  • A set of variables (nodes) and directed links;
  • Nodes/links form a directed acyclic graph;
  • Each variable has a finite set of mutually exclusive states; and
  • A Conditional Probability Table (CPT) representing discrete conditional probabilities (i.e., likelihoods based on prior information or past experiences) is attached to each parent node.