Bayesian Networks are probabilistic graphical models that represent a set of random variables through a directed acyclic graph (DAG) and factorize their joint probability distribution.
Formally, they define the distribution as the product of the conditional probabilities of each variable given its parents in the graph.
The structure of the network encodes independence assumptions that enable efficient probabilistic inference and learning.
Bayesian Networks are used for diagnosis, prognosis, and decision support, allowing the calculation of posterior probabilities given observations.
Definition:
A Bayesian Network is a probabilistic model that represents a joint probability distribution over a set of variables through a directed acyclic graph, where the distribution is decomposed as the product of the conditional probabilities of each variable given its parent factors.
Source:
Jensen, F. V. (2001). Bayesian Networks and Decision Graphs. Springer.