Class OnlineLearning

Adapts the parameters of a Bayesian network, using Bayesian statistics.

Inheritance

System.Object

OnlineLearning

Inherited Members

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: BayesServer.Learning.Parameters

Assembly: BayesServer.Learning.Parameters.dll

Syntax

public sealed class OnlineLearning

Constructors

OnlineLearning(Network, IInferenceFactory)

Initializes a new instance of the OnlineLearning class.

Declaration

public OnlineLearning(Network network, IInferenceFactory factory)

Parameters

Type	Name	Description
Network	network	The network whose parameters are being adapted.
IInferenceFactory	factory	The inference factory used to create inference engines in cases when learning requires inference.

Remarks

Learning uses inference as a subroutine, and creates one or more inference engines via the factory parameter.

Properties

Evidence

Gets the evidence used internally. Setting evidence on this instance, and passing it to Adapt saves a copy.

Declaration

public IEvidence Evidence { get; }

Property Value

Type	Description
IEvidence

Methods

Adapt(IEvidence, OnlineLearningOptions)

Adapt the parameters of a Bayesian network using Bayesian statistics.

Declaration

public void Adapt(IEvidence evidence, OnlineLearningOptions options)

Parameters

Type	Name	Description
IEvidence	evidence	The evidence to learn.
OnlineLearningOptions	options	Options that affect how parameters are adapted.

Remarks

For nodes to be adapted, they must have Experience tables assigned (and optionally fading tables).

In the case a discrete node, the experience table combined with the probability are used to create a Dirichlet distribution. This distribution acts as a prior during the Bayesian inference process.