Package | Description |
---|---|
de.jstacs.classifiers.differentiableSequenceScoreBased |
Provides the classes for
Classifier s that are based on SequenceScore s.It includes a sub-package for discriminative objective functions, namely conditional likelihood and supervised posterior, and a separate sub-package for the parameter priors, that can be used for the supervised posterior. |
de.jstacs.classifiers.differentiableSequenceScoreBased.gendismix |
Provides an implementation of a classifier that allows to train the parameters of a set of
DifferentiableStatisticalModel s by
a unified generative-discriminative learning principle. |
de.jstacs.classifiers.differentiableSequenceScoreBased.logPrior |
Provides a general definition of a parameter log-prior and a number of implementations of Laplace and Gaussian priors.
|
de.jstacs.classifiers.differentiableSequenceScoreBased.msp |
Provides an implementation of a classifier that allows to train the parameters of a set of
DifferentiableStatisticalModel s either
by maximum supervised posterior (MSP) or by maximum conditional likelihood (MCL). |
de.jstacs.classifiers.differentiableSequenceScoreBased.sampling |
Provides the classes for
AbstractScoreBasedClassifier s that are based on
SamplingDifferentiableStatisticalModel s
and that sample parameters using the Metropolis-Hastings algorithm. |
de.jstacs.sequenceScores.statisticalModels.trainable |
Provides all
TrainableStatisticalModel s, which can
be learned from a single DataSet . |
Modifier and Type | Field and Description |
---|---|
protected LogPrior |
DiffSSBasedOptimizableFunction.prior
The prior that is used in this function.
|
Constructor and Description |
---|
DiffSSBasedOptimizableFunction(int threads,
DifferentiableSequenceScore[] score,
DataSet[] data,
double[][] weights,
LogPrior prior,
boolean norm,
boolean freeParams)
Creates an instance with the underlying infrastructure.
|
Modifier and Type | Field and Description |
---|---|
protected LogPrior |
GenDisMixClassifier.prior
The prior that is used in this classifier.
|
Modifier and Type | Method and Description |
---|---|
static GenDisMixClassifier[] |
GenDisMixClassifier.create(GenDisMixClassifierParameterSet params,
LogPrior prior,
double[] weights,
DifferentiableStatisticalModel[]... functions)
This method creates an array of GenDisMixClassifiers by using the cross-product of the given
DifferentiableStatisticalModel s. |
void |
GenDisMixClassifier.setPrior(LogPrior prior)
This method set a new prior that should be used for optimization.
|
Constructor and Description |
---|
GenDisMixClassifier(GenDisMixClassifierParameterSet params,
LogPrior prior,
double[] beta,
DifferentiableStatisticalModel... score)
The main constructor.
|
GenDisMixClassifier(GenDisMixClassifierParameterSet params,
LogPrior prior,
double lastScore,
double[] beta,
DifferentiableSequenceScore... score)
This constructor creates an instance and sets the value of the last (external) optimization.
|
GenDisMixClassifier(GenDisMixClassifierParameterSet params,
LogPrior prior,
double lastScore,
double[] beta,
DifferentiableStatisticalModel... score)
This constructor creates an instance and sets the value of the last (external) optimization.
|
GenDisMixClassifier(GenDisMixClassifierParameterSet params,
LogPrior prior,
double genBeta,
double disBeta,
double priorBeta,
DifferentiableStatisticalModel... score)
This convenience constructor agglomerates the
genBeta, disBeta, and priorBeta into an array and calls the main constructor. |
GenDisMixClassifier(GenDisMixClassifierParameterSet params,
LogPrior prior,
LearningPrinciple key,
DifferentiableStatisticalModel... score)
This convenience constructor creates an array of weights for an elementary learning principle and calls the main constructor.
|
LogGenDisMixFunction(int threads,
DifferentiableSequenceScore[] score,
DataSet[] data,
double[][] weights,
LogPrior prior,
double[] beta,
boolean norm,
boolean freeParams)
The constructor for creating an instance that can be used in an
Optimizer . |
OneDataSetLogGenDisMixFunction(int threads,
DifferentiableSequenceScore[] score,
DataSet data,
double[][] weights,
LogPrior prior,
double[] beta,
boolean norm,
boolean freeParams)
The constructor for creating an instance that can be used in an
Optimizer . |
Modifier and Type | Class and Description |
---|---|
class |
CompositeLogPrior
This class implements a composite prior that can be used for DifferentiableStatisticalModel.
|
class |
DoesNothingLogPrior
This class defines a
LogPrior that does not penalize any parameter. |
class |
SeparateGaussianLogPrior
Class for a
LogPrior that defines a Gaussian prior on the parameters
of a set of DifferentiableStatisticalModel s
and a set of class parameters. |
class |
SeparateLaplaceLogPrior
Class for a
LogPrior that defines a Laplace prior on the parameters
of a set of DifferentiableStatisticalModel s
and a set of class parameters. |
class |
SeparateLogPrior
Abstract class for priors that penalize each parameter value independently
and have some variances (and possible means) as hyperparameters.
|
class |
SimpleGaussianSumLogPrior
This class implements a prior that is a product of Gaussian distributions
with mean 0 and equal variance for each parameter.
|
Modifier and Type | Method and Description |
---|---|
abstract LogPrior |
LogPrior.getNewInstance()
This method returns an empty new instance of the current prior.
|
LogPrior |
DoesNothingLogPrior.getNewInstance() |
Constructor and Description |
---|
MSPClassifier(GenDisMixClassifierParameterSet params,
LogPrior prior,
DifferentiableSequenceScore... score)
The default constructor that creates a new
MSPClassifier from a
given parameter set, a prior and DifferentiableSequenceScore s for the
classes. |
MSPClassifier(GenDisMixClassifierParameterSet params,
LogPrior prior,
double lastScore,
DifferentiableSequenceScore... score)
This constructor that creates a new
MSPClassifier from a
given parameter set, a prior and DifferentiableSequenceScore s for the
classes. |
Constructor and Description |
---|
SamplingGenDisMixClassifier(SamplingGenDisMixClassifierParameterSet params,
BurnInTest burnInTest,
double[] classVariances,
LogPrior prior,
double[] beta,
SamplingDifferentiableStatisticalModel... scoringFunctions)
Creates a new
SamplingGenDisMixClassifier using the external parameters
params , a burn-in test, a set of sampling variances for the different classes,
a prior on the parameters, weights beta for the three components of the
LogGenDisMixFunction , i.e., likelihood, conditional likelihood, and prior,
and scoring functions that model the distribution for each of the classes. |
SamplingGenDisMixClassifier(SamplingGenDisMixClassifierParameterSet params,
BurnInTest burnInTest,
double[] classVariances,
LogPrior prior,
LearningPrinciple principle,
SamplingDifferentiableStatisticalModel... scoringFunctions)
Creates a new
SamplingGenDisMixClassifier using the external parameters
params , a burn-in test, a set of sampling variances for the different classes,
a prior on the parameters, a learning principle,
and scoring functions that model the distribution for each of the classes. |
Constructor and Description |
---|
DifferentiableStatisticalModelWrapperTrainSM(DifferentiableStatisticalModel nsf,
int threads,
byte algo,
AbstractTerminationCondition tc,
double lineps,
double startD,
LogPrior prior)
Constructor that creates an instance with the user given parameters.
|