Bayes Server .NET Library Help 
The Bayes Server Class Library is a .NET library for Bayesian networks and Dynamic Bayesian networks.
For code samples, please visit the Bayes Server code center
Namespace  Description 

BayesServer 
Contains classes and interfaces for defining the structure and distributions
of a Bayesian network, and to save and load them.
To perform inference, such as calculating posterior probabilities and loglikelihoods
see the BayesServer.Inference namespace.

BayesServer.Analysis 
Contains classes for performing analysis tasks that require inference and/or data,
such as calculating value of information.

BayesServer.Data 
Provides interfaces/classes for handling data.

BayesServer.Data.Discovery 
Contains classes and interfaces for generating variables from data.

BayesServer.Data.Discovery.Discretization 
Contains classes and interfaces for discretizing continuous data.

BayesServer.Data.Distributed 
Contains classes and interfaces for distributed data driven processes such as distributed parameter learning.

BayesServer.Data.Sampling 
Contains classes for sampling data from Bayesian networks and Dynamic Bayesian networks. See TakeSample for sample code.

BayesServer.Data.TimeSeries 
Contains classes and interfaces for manipulating time series data.

BayesServer.Distributed 
Contains classes and interfaces for distributed algorithms such as distributed parameter learning.

BayesServer.Inference 
Contains interfaces for performing probabilistic inference with a
Bayesian network, such as calculating posterior probabilities and loglikelihoods.
See the RelevanceTreeInference class for an algorithm that implements the necessary interfaces.

BayesServer.Inference.Approximate 
Contains classes and interfaces for performing approximate probabilistic inference with a
Bayesian network, such as calculating posterior probabilities and loglikelihoods.
See the LoopyBeliefInference class for an algorithm that implements the necessary interfaces.

BayesServer.Inference.Approximate.LikelihoodSampling 
Contains classes for performing inference with Bayesian networks and Dynamic Bayesian networks using an approximate inference method called Likelihood sampling.

BayesServer.Inference.Approximate.LoopyBelief 
Contains classes for performing inference with Bayesian networks and Dynamic Bayesian networks using an approximate inference method based on loopy belief propagation.

BayesServer.Inference.RelevanceTree 
Provides an exact probabilistic inference algorithm for Bayesian networks and Dynamic Bayesian networks, that can compute multiple distributions more efficiently
than the VariableEliminationInference algorithm.

BayesServer.Inference.VariableElimination 
Provides an exact probabilistic inference algorithm for Bayesian networks, loosely based on the Variable Elimination algorithm.

BayesServer.Learning.Parameters 
Provides parameter learning for Bayesian networks and Dynamic Bayesian networks. See Learn for sample code.

BayesServer.Learning.Structure 
Contains classes for learning the structure (links) of a Bayesian network or Dynamic Bayesian network.

BayesServer.Learning.Structure.ChowLiu 
Contains classes for learning the structure (links) of a Bayesian network or Dynamic Bayesian network using the ChowLiu algorithm.

BayesServer.Learning.Structure.Features 
Contains classes to perform feature selection.

BayesServer.Learning.Structure.Hierarchical  
BayesServer.Learning.Structure.Independence 
Contains classes concerned with independence/conditional independence testing.

BayesServer.Learning.Structure.PC 
Contains classes for learning the structure (links) of a Bayesian network or Dynamic Bayesian network using the PC algorithm.

BayesServer.Learning.Structure.Search  
BayesServer.Learning.Structure.TAN 
Contains classes for learning the structure (links) of a Bayesian network or Dynamic Bayesian network using the Tree Augmented Naive Bayes algorithm.

BayesServer.Statistics 
Contains interfaces and classes for performing statistical/probabilistic tests.
