Skip to main content

Module graphical_models

qualia_core_db::solvers::learning

Module graphical_models

Expand description

Probabilistic graphical models (PRML ch 8) — relational inference over discrete variables. The governance topology is relational and lives in the edges, so a factor graph with belief propagation is the native inference for it.

factor_graph — discrete factor graph + sum-product belief propagation.

Re-exports§

pub use factor_graph::Factor;
pub use factor_graph::FactorGraph;

Modules§

factor_graph: Discrete factor graphs + the sum-product algorithm (PRML ch 8.4) — belief propagation for marginal inference. Exact on a tree, loopy (iterated) otherwise.