Package | Description |
---|---|
gov.sandia.cognition.learning.experiment |
Provides experiments for validating the performance of learning algorithms.
|
gov.sandia.cognition.learning.function.cost |
Provides cost functions.
|
gov.sandia.cognition.learning.performance |
Provides performance measures.
|
gov.sandia.cognition.learning.performance.categorization |
Provides performance measures for categorizers.
|
Modifier and Type | Class and Description |
---|---|
class |
LearnerRepeatExperiment<InputDataType,LearnedType,StatisticType,SummaryType>
Runs an experiment where the same learner is evaluated multiple times on
the same data.
|
class |
LearnerValidationExperiment<InputDataType,FoldDataType,LearnedType,StatisticType,SummaryType>
The
LearnerValidationExperiment class implements an experiment where
a supervised machine learning algorithm is evaluated by applying it to a set
of folds created from a given set of data. |
class |
OnlineLearnerValidationExperiment<DataType,LearnedType,StatisticType,SummaryType>
Implements an experiment where an incremental supervised machine learning
algorithm is evaluated by applying it to a set of data by successively
testing on each item and then training on it.
|
class |
ParallelLearnerValidationExperiment<InputDataType,FoldDataType,LearnedType,StatisticType,SummaryType>
Parallel version of the LearnerValidationExperiment class that executes
the validations experiments across available cores and hyperthreads.
|
class |
SupervisedLearnerValidationExperiment<InputType,OutputType,StatisticType,SummaryType>
The
SupervisedLearnerValidationExperiment class extends the
LearnerValidationExperiment class to provide a easy way to create
a learner validation experiment for supervised learning. |
Modifier and Type | Field and Description |
---|---|
protected PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> |
LearnerComparisonExperiment.performanceEvaluator
The evaluator to use to compute the performance of the learned object on
each fold.
|
protected PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends InputDataType>,? extends StatisticType> |
LearnerRepeatExperiment.performanceEvaluator
The evaluator to use to compute the performance of the learned object on
each fold.
|
protected PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> |
LearnerValidationExperiment.performanceEvaluator
The evaluator to use to compute the performance of the learned object on
each fold.
|
protected PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends DataType>,? extends StatisticType> |
OnlineLearnerValidationExperiment.performanceEvaluator
The evaluator to use to compute the performance of the learned object on
each fold.
|
Modifier and Type | Method and Description |
---|---|
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> |
LearnerComparisonExperiment.getPerformanceEvaluator()
Gets the performance evaluator to apply to each fold.
|
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends InputDataType>,? extends StatisticType> |
LearnerRepeatExperiment.getPerformanceEvaluator()
Gets the performance evaluator to apply to each fold.
|
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> |
LearnerValidationExperiment.getPerformanceEvaluator()
Gets the performance evaluator to apply to each fold.
|
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends DataType>,? extends StatisticType> |
OnlineLearnerValidationExperiment.getPerformanceEvaluator()
Gets the performance evaluator to apply to each fold.
|
Modifier and Type | Method and Description |
---|---|
void |
OnlineLearnerValidationExperiment.setPerformanceEvaluator(PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends DataType>,? extends StatisticType> performanceEvaluator)
Sets the performance evaluator to apply to each fold.
|
void |
LearnerComparisonExperiment.setPerformanceEvaluator(PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> performanceEvaluator)
Sets the performance evaluator to apply to each fold.
|
void |
LearnerValidationExperiment.setPerformanceEvaluator(PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> performanceEvaluator)
Sets the performance evaluator to apply to each fold.
|
void |
LearnerRepeatExperiment.setPerformanceEvaluator(PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends InputDataType>,? extends StatisticType> performanceEvaluator)
Sets the performance evaluator to apply to each fold.
|
Constructor and Description |
---|
LearnerComparisonExperiment(ValidationFoldCreator<InputDataType,FoldDataType> foldCreator,
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> performanceEvaluator,
NullHypothesisEvaluator<java.util.Collection<? extends StatisticType>> statisticalTest,
Summarizer<? super StatisticType,? extends SummaryType> summarizer)
Creates a new instance of LearnerComparisonExperiment.
|
LearnerRepeatExperiment(int numTrials,
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends InputDataType>,? extends StatisticType> performanceEvaluator,
Summarizer<? super StatisticType,? extends SummaryType> summarizer)
Creates a new instance of LearnerRepeatExperiment.
|
LearnerValidationExperiment(ValidationFoldCreator<InputDataType,FoldDataType> foldCreator,
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> performanceEvaluator,
Summarizer<? super StatisticType,? extends SummaryType> summarizer)
Creates a new instance of SupervisedLearnerExperiment.
|
OnlineLearnerValidationExperiment(PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends DataType>,? extends StatisticType> performanceEvaluator,
Summarizer<? super StatisticType,? extends SummaryType> summarizer)
Creates a new instance of IncrementalLearnerValidationExperiment.
|
ParallelLearnerValidationExperiment(ValidationFoldCreator<InputDataType,FoldDataType> foldCreator,
PerformanceEvaluator<? super LearnedType,? super java.util.Collection<? extends FoldDataType>,? extends StatisticType> performanceEvaluator,
Summarizer<? super StatisticType,? extends SummaryType> summarizer)
Creates a new instance of ParallelLearnerValidationExperiment.
|
SupervisedLearnerComparisonExperiment(ValidationFoldCreator<InputOutputPair<InputType,OutputType>,InputOutputPair<InputType,OutputType>> foldCreator,
PerformanceEvaluator<? super Evaluator<? super InputType,OutputType>,? super java.util.Collection<? extends InputOutputPair<InputType,OutputType>>,? extends StatisticType> performanceEvaluator,
NullHypothesisEvaluator<java.util.Collection<? extends StatisticType>> statisticalTest,
Summarizer<? super StatisticType,? extends SummaryType> summarizer)
Creates a new instance of
SupervisedLearnerComparisonExperiment . |
SupervisedLearnerValidationExperiment(ValidationFoldCreator<InputOutputPair<InputType,OutputType>,InputOutputPair<InputType,OutputType>> foldCreator,
PerformanceEvaluator<? super Evaluator<? super InputType,? extends OutputType>,? super java.util.Collection<? extends InputOutputPair<InputType,OutputType>>,? extends StatisticType> performanceEvaluator,
Summarizer<? super StatisticType,? extends SummaryType> summarizer)
Creates a new instance of
SupervisedLearnerValidationExperiment . |
Modifier and Type | Interface and Description |
---|---|
interface |
DifferentiableCostFunction
The
DifferentiableCostFunction is a cost function that can
be differentiated. |
interface |
ParallelizableCostFunction
Interface describing a cost function that can (largely) be computed in
parallel.
|
interface |
SupervisedCostFunction<InputType,TargetType>
A type of CostFunction normally used in supervised-learning applications.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractParallelizableCostFunction
Partial implementation of the ParallelizableCostFunction
|
class |
AbstractSupervisedCostFunction<InputType,TargetType>
Partial implementation of SupervisedCostFunction
|
class |
MeanL1CostFunction
Cost function that evaluates the mean 1-norm error (absolute value of
difference) weighted by a sample "weight" that is embedded in each sample.
|
class |
MeanSquaredErrorCostFunction
The MeanSquaredErrorCostFunction implements a cost function for functions
that take as input a vector and return a vector.
|
class |
ParallelizedCostFunctionContainer
A cost function that automatically splits a ParallelizableCostFunction
across multiple cores/processors to speed up computation.
|
class |
SumSquaredErrorCostFunction
This is the sum-squared error cost function
|
Modifier and Type | Interface and Description |
---|---|
interface |
SupervisedPerformanceEvaluator<InputType,TargetType,EstimateType,ResultType>
The
SupervisedPerformanceEvaluator interface extends the
PerformanceEvaluator interface for performance evaluations of
supervised machine learning algorithms where the target type is evaluated
against the estimated type produced by the evaluator. |
Modifier and Type | Class and Description |
---|---|
class |
AbstractSupervisedPerformanceEvaluator<InputType,TargetType,EstimateType,ResultType>
The
AbstractSupervisedPerformanceEvaluator class contains an
abstract implementation of the SupervisedPerformanceEvaluator class. |
class |
MeanAbsoluteErrorEvaluator<InputType>
The
MeanAbsoluteError class implements a method for computing the
performance of a supervised learner for a scalar function by the mean
absolute value between the target and estimated outputs. |
class |
MeanSquaredErrorEvaluator<InputType>
The
MeanSquaredError class implements the method for computing the
performance of a supervised learner for a scalar function by the mean squared
between the target and estimated outputs. |
class |
MeanZeroOneErrorEvaluator<InputType,DataType>
The
MeanZeroOneErrorEvaluator class implements a method for
computing the performance of a supervised learner by the mean number of
incorrect values between the target and estimated outputs. |
class |
RootMeanSquaredErrorEvaluator<InputType>
The
RootMeanSquaredErrorEvaluator class implements a method for
computing the performance of a supervised learner for a scalar function by
the root mean squared error (RMSE or RSE) between the target and estimated
outputs. |
Modifier and Type | Field and Description |
---|---|
protected PerformanceEvaluator<? super ObjectType,? super DataType,?> |
AnytimeBatchLearnerValidationPerformanceReporter.performanceEvaluator
The performance evaluator.
|
Modifier and Type | Method and Description |
---|---|
PerformanceEvaluator<? super ObjectType,? super DataType,?> |
AnytimeBatchLearnerValidationPerformanceReporter.getPerformanceEvaluator()
Gets the performance evaluator.
|
Modifier and Type | Method and Description |
---|---|
void |
AnytimeBatchLearnerValidationPerformanceReporter.setPerformanceEvaluator(PerformanceEvaluator<? super ObjectType,? super DataType,?> performanceEvaluator)
Sets the performance evaluator.
|
Constructor and Description |
---|
AnytimeBatchLearnerValidationPerformanceReporter(PerformanceEvaluator<? super ObjectType,? super DataType,?> performanceEvaluator,
DataType validationData)
Creates a new
AnytimeBatchLearnerValidationPerformanceReporter that
reports to the given print stream using the default format. |
AnytimeBatchLearnerValidationPerformanceReporter(PerformanceEvaluator<? super ObjectType,? super DataType,?> performanceEvaluator,
DataType validationData,
java.io.PrintStream out)
Creates a new
AnytimeBatchLearnerValidationPerformanceReporter that
reports to the given print stream using the default format. |
AnytimeBatchLearnerValidationPerformanceReporter(PerformanceEvaluator<? super ObjectType,? super DataType,?> performanceEvaluator,
DataType validationData,
java.io.PrintStream out,
java.lang.String format)
Creates a new
AnytimeBatchLearnerValidationPerformanceReporter that
reports to the given print stream and format. |
AnytimeBatchLearnerValidationPerformanceReporter(PerformanceEvaluator<? super ObjectType,? super DataType,?> performanceEvaluator,
DataType validationData,
java.lang.String format)
Creates a new
AnytimeBatchLearnerValidationPerformanceReporter that
reports to System.out and the given format. |
Modifier and Type | Class and Description |
---|---|
class |
ConfusionMatrixPerformanceEvaluator<InputType,CategoryType>
A performance evaluator that builds a confusion matrix.
|
static class |
DefaultBinaryConfusionMatrix.PerformanceEvaluator<InputType>
An implementation of the
SupervisedPerformanceEvaluator interface
for creating a DefaultBinaryConfusionMatrix . |