gov.sandia.cognition.statistics.bayesian
Interface BayesianRegression<OutputType,PosteriorType extends Distribution<? extends Vector>>

Type Parameters:
OutputType - Type of outputs to consider, typically a Double
PosteriorType - Posterior distribution of the weights given the observed InputOutputPairs
All Superinterfaces:
BatchLearner<Collection<? extends InputOutputPair<? extends Vectorizable,OutputType>>,PosteriorType>, BayesianEstimator<InputOutputPair<? extends Vectorizable,OutputType>,Vector,PosteriorType>, Cloneable, CloneableSerializable, Serializable
All Known Implementing Classes:
BayesianLinearRegression, BayesianLinearRegression.IncrementalEstimator, BayesianRobustLinearRegression, BayesianRobustLinearRegression.IncrementalEstimator

@PublicationReferences(references={@PublicationReference(author="Christopher M. Bishop",title="Pattern Recognition and Machine Learning",type=Book,year=2006,pages={152,159}),@PublicationReference(author="Hanna M. Wallach",title="Introduction to Gaussian Process Regression",type=Misc,year=2005,url="http://www.cs.umass.edu/~wallach/talks/gp_intro.pdf"),@PublicationReference(author="Wikipedia",title="Bayesian linear regression",type=WebPage,year=2010,url="http://en.wikipedia.org/wiki/Bayesian_linear_regression")})
public interface BayesianRegression<OutputType,PosteriorType extends Distribution<? extends Vector>>
extends BayesianEstimator<InputOutputPair<? extends Vectorizable,OutputType>,Vector,PosteriorType>

A type of regression algorithm maps a Vector space, and the weights of this Vector space are represented as a posterior distribution given the observed InputOutputPairs. The system can also estimate the predictive distribution of future data given the weight posterior for a desired input value.

Since:
3.0
Author:
Kevin R. Dixon

Method Summary
 Distribution<OutputType> createConditionalDistribution(Vectorizable input, Vector weights)
          Creates the distribution from which the outputs are generated, given the weights and the input to consider.
 Evaluator<? super Vectorizable,? extends ClosedFormDistribution<OutputType>> createPredictiveDistribution(PosteriorType posterior)
          Creates the predictive distribution of outputs given the weight posterior
 
Methods inherited from interface gov.sandia.cognition.learning.algorithm.BatchLearner
learn
 
Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable
clone
 

Method Detail

createConditionalDistribution

Distribution<OutputType> createConditionalDistribution(Vectorizable input,
                                                       Vector weights)
Creates the distribution from which the outputs are generated, given the weights and the input to consider.

Parameters:
input - Input to condition on
weights - Weights that determine the mean
Returns:
Conditional distribution from which outputs are generated.

createPredictiveDistribution

Evaluator<? super Vectorizable,? extends ClosedFormDistribution<OutputType>> createPredictiveDistribution(PosteriorType posterior)
Creates the predictive distribution of outputs given the weight posterior

Parameters:
posterior - Posterior distribution of weights.
Returns:
Predictive distribution of outputs given the posterior.