aima.core.probability.bayes.approx

Interface BayesSampleInference

All Known Implementing Classes:

GibbsAsk, LikelihoodWeighting, RejectionSampling

public interface BayesSampleInference

General interface to be implemented by approximate Bayesian Inference algorithms.

Author:

Ciaran O'Reilly

Method Summary

Modifier and Type	Method and Description
CategoricalDistribution	ask(RandomVariable[] X, AssignmentProposition[] observedEvidence, BayesianNetwork bn, int N)

Method Detail

ask

CategoricalDistribution ask(RandomVariable[] X,
                            AssignmentProposition[] observedEvidence,
                            BayesianNetwork bn,
                            int N)

Parameters:

X - the query variables.

observedEvidence - observed values for variables E.

bn - a Bayes net with variables {X} ∪ E ∪ Y /* Y = hidden variables

N - the total number of samples to be generated

Returns:

an estimate of P(X|e).