Directed Graphical Statistical Model Family
Jump to navigation Jump to search
- See: Statistical Model.
- Directed graphical models (also known as Bayesian networks) represent a joint distribution over random variables by a product of normalized conditional probability distributions (one for each "child" variable, conditioned on the other "parent" variables that are connected by an incoming directed edge). They are convenient generative models when variable values can be generated by an ordered iteration of the graph nodes from "parent" variables to "child" variables.