Glossary

BN: Bayesian Network
UG: Undirected Graph
dBN: Dynamic Bayesian Network
DAG: Directed Acyclic Graph
PDAG: Partially Directed Acyclic Graph
EM: Expectation-Maximization algorithm, dealing with missng data
MLE: Maximum Likelihood Estimation
AIC: Akaike Information Criterion
BIC: Bayesian Information Criterion
O3PRM: Open Object Oriented Probabilistic Relational Model, Object oriented language for specification of PRM
MRF: Markov Random Field
ID: Influence Diagram
LIMID: Limited Memory Influence Diagram
CN: Credal Network
PRM: Probabilistic Relational Model
API: Application Programming Interface
Graphical model: A probabilistic model for which a graph expresses the conditional dependence structure between random variables.
Bayesian network: A probabilistic graphical model that represents a set of random variables and their conditional dependencies in the form of a directed acyclic graph (DAG).
Markov random field: A type of undirected graphical model that represents a set of random variables and their conditional dependencies in the form of an undirected graph (UG).
Influence diagram: A type of graphical model that represents a set of random variables and their conditional dependencies in the form of a directed acyclic graph.
Limited memory influence diagram: A type of influence diagram
Credal network: A type of graphical model that represents a set of random variables and their conditional dependencies in the form of a directed acyclic graph with sets of probability distributions.
Dynamic Bayesian network: A type of graphical model that represents a set of random variables and their conditional dependencies in the form of a directed acyclic graph that changes over (discrete) time. It is a generalisation of Markov Chain (with partial observation).
Probabilistic relational model: A type of graphical model that represents a set of random variables and their conditional dependencies using graphs and patterns (such as relational databases, or Object Oriented programming language).