• Home Page
• Documentation
  • bnlearn manual
  • references
  • bayesian networks
• Examples
• About the Author

Constraint-based learning algorithms

• Grow-Shrink (GS) algorithm
• Incremental Association Marklov Blanket (IAMB) algorithmi
• Fast Incremental Association Marklov Blanket (Fast-IAMB) algorithm
• Interleaved Incremental Association Marklov Blanket (Inter-IAMB) algorithm

Score-based learning algorithms

• Hill Climbing (HC) algorithm

Hybrid learning algorithms

• Max-Min Hill Climbing (MMHC) algorithm
• Two-Phase Restricted Maximization (RSMAX2) algorithm

Neighbourhood discovery algorithms

• Max-Min Parents and Children (MMPC) learning algorithm

Conditional independence tests

• list of the available conditional independence tests and the respective labels
• the ci.test function and its parameters

Score functions

• list of the available score functions and the respective labels
• the score function and its parameters

Parameter estimation

• Bayesian network's parameters estimation

Inference and Model Validation

• generic parametric and nonparametric bootstrap
• arc strength and direction confidence via nonparametric bootstrap
• conditional probability queries
• learning strategy and network evaluation through cross-validation
• log-likelihood, AIC and BIC evaluation for arbitrary data

Random graph generation

• random graph generation (with a specified node ordering)
• random graph generation (uniform sampling from the space of directed acyclic graphs)

Random data generation

• random data generation from a specified network structure

Plotting functions

• plots of simple networks based on traditional graphics functions
• plots of large networks based on Rgraphviz functions
• diagnostic plots for the fitted models based on lattice functions

Interactions with othe R packages

• use the parallel computing facilities provided by the snow package to speed up learning algorithms
• import networks from and export to the deal package