Difference between revisions of "Belief Propagation"
From Cohen Courses
Jump to navigationJump to searchm (moved BeliefPropagation to Belief Propagation: adding space) |
|||
| Line 1: | Line 1: | ||
| − | This is a [[Category:: | + | This is a [[Category::Method]] proposed in [[RelatedPaper::Judea Pearl, 1982: Reverend Bayes on inference engines: A distributed hierarchical approach, AAAI 1982]]. |
Belief Propagation is a message passing inference method for statistical graphical models (e.g. Markov random fields). The basic idea is to compute the marginal distribution of unobserved nodes, based on the conditional distribution of observed nodes. A simple and intuitive case is when the graphical model is both a factor graph and a tree, then it will can compute the exact marginals. | Belief Propagation is a message passing inference method for statistical graphical models (e.g. Markov random fields). The basic idea is to compute the marginal distribution of unobserved nodes, based on the conditional distribution of observed nodes. A simple and intuitive case is when the graphical model is both a factor graph and a tree, then it will can compute the exact marginals. | ||
Revision as of 21:48, 26 September 2011
This is a Method proposed in Judea Pearl, 1982: Reverend Bayes on inference engines: A distributed hierarchical approach, AAAI 1982.
Belief Propagation is a message passing inference method for statistical graphical models (e.g. Markov random fields). The basic idea is to compute the marginal distribution of unobserved nodes, based on the conditional distribution of observed nodes. A simple and intuitive case is when the graphical model is both a factor graph and a tree, then it will can compute the exact marginals.
