Bayesian network(1)

기본 단어 정리

probabilistic GMs includes BNs

node = random variable
edges = probabilistic dependency

GMs with undirected edges :   Markov random fields

Markov blanket : 

every node is only dependent on its parents, children and children's parents

DAG
   - nodes
   - directed edges : statistical dependence = "influence"


 * each variable is independent of its non-descendents in the graph given the state of its parents.

 * For discrete random variables, this conditional probability is often represented by a table, listing the local probability that a child node takes on each of the feasible values  for each combination of values of its parents.

A Bayesian network B is an annotated acyclic graph that represents a JPD over a set of random variables V. The network is defined by a pair B =<G, θ>
G : Graph
θ : set of parameter ex) θxi|πi = PB(xi|πi)