Package de.jstacs.classifiers.differentiableSequenceScoreBased.sampling

Provides the classes for AbstractScoreBasedClassifiers that are based on SamplingDifferentiableStatisticalModels and that sample parameters using the Metropolis-Hastings algorithm.

See: Description

Class Summary

Class	Description
SamplingGenDisMixClassifier	A classifier that samples its parameters from a LogGenDisMixFunction using the Metropolis-Hastings algorithm.
SamplingGenDisMixClassifierParameterSet	ParameterSet to instantiate a SamplingGenDisMixClassifier.
SamplingScoreBasedClassifier	A classifier that samples the parameters of SamplingDifferentiableStatisticalModels by the Metropolis-Hastings algorithm.
SamplingScoreBasedClassifierParameterSet	ParameterSet to instantiate a SamplingScoreBasedClassifier.

Enum Summary

Enum	Description
SamplingScoreBasedClassifier.SamplingScheme	Sampling scheme for sampling the parameters of the scoring functions.

Package de.jstacs.classifiers.differentiableSequenceScoreBased.sampling Description

Provides the classes for AbstractScoreBasedClassifiers that are based on SamplingDifferentiableStatisticalModels and that sample parameters using the Metropolis-Hastings algorithm. The abstract base class of all such classifiers is the SamplingScoreBasedClassifier, while the SamplingGenDisMixClassifier provides an implementation for the unified generative-discriminative learning principle.

Since:

Jstacs 1.5