gov.sandia.cognition.learning.algorithm.ensemble

Class MultiCategoryAdaBoost<InputType,CategoryType>

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.algorithm.AbstractIterativeAlgorithm

gov.sandia.cognition.algorithm.AbstractAnytimeAlgorithm<ResultType>

gov.sandia.cognition.learning.algorithm.AbstractAnytimeBatchLearner<java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>>,ResultType>

gov.sandia.cognition.learning.algorithm.AbstractAnytimeSupervisedBatchLearner<InputType,CategoryType,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>

gov.sandia.cognition.learning.algorithm.ensemble.MultiCategoryAdaBoost<InputType,CategoryType>

Type Parameters:

InputType - The type of input that the weak learner can learn over.

CategoryType - The type of categories to learn over.

All Implemented Interfaces:

AnytimeAlgorithm<WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>, IterativeAlgorithm, StoppableAlgorithm, AnytimeBatchLearner<java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>, BatchLearner<java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>, BatchLearnerContainer<BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>>>, SupervisedBatchLearner<InputType,CategoryType,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

@PublicationReference(author={"Yoav Freund","Robert E.Schapire"},
                      title="A decision-theoretic generalization of on-line learning and an application to boosting",
                      publication="Journal of Computer and System Sciences",
                      notes="Volume 55, Number 1",
                      year=1997,
                      pages={119,139},
                      type=Journal,
                      url="http://www.cse.ucsd.edu/~yfreund/papers/adaboost.pdf")
public class MultiCategoryAdaBoost<InputType,CategoryType>
extends AbstractAnytimeSupervisedBatchLearner<InputType,CategoryType,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>
implements BatchLearnerContainer<BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>>>

An implementation of a multi-class version of the Adaptive Boosting (AdaBoost) algorithm, known as AdaBoost.M1. Note that the "weak learner" in this version of AdaBoost requires a weighted error rate that is greater than 0.5 to be accepted into the ensemble and for learning to continue.

Since:

3.2.0

Author:

Justin Basilico

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static int	DEFAULT_MAX_ITERATIONS The default maximum number of iterations is 100.
protected WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>	ensemble The ensemble learned by the algorithm.
protected BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>>	weakLearner The "weak learner" that must learn from the weighted input-output pairs on each iteration.
protected java.util.ArrayList<DefaultWeightedInputOutputPair<InputType,CategoryType>>	weightedData An array list containing the weighted version of the data.

Fields inherited from class gov.sandia.cognition.learning.algorithm.AbstractAnytimeBatchLearner

data, keepGoing

Fields inherited from class gov.sandia.cognition.algorithm.AbstractAnytimeAlgorithm

maxIterations

Fields inherited from class gov.sandia.cognition.algorithm.AbstractIterativeAlgorithm

DEFAULT_ITERATION, iteration

Constructor Summary

Constructors

Constructor and Description
MultiCategoryAdaBoost() Creates a new MultiCategoryAdaBoost with default parameters and a null weak learner.
MultiCategoryAdaBoost(BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>> weakLearner, int maxIterations) Creates a new MultiCategoryAdaBoost with the given parameters.

Method Summary

Modifier and Type	Method and Description
protected void	cleanupAlgorithm() Called to clean up the learning algorithm's state after learning has finished.
BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>>	getLearner() Gets the learner contained in this object.
WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>	getResult() Gets the current result of the algorithm.
BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>>	getWeakLearner() Gets the weak learner that is passed the weighted training data on each step of the algorithm.
protected boolean	initializeAlgorithm() Called to initialize the learning algorithm's state based on the data that is stored in the data field.
void	setWeakLearner(BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>> weakLearner) Sets the weak learner that is passed the weighted training data on each step of the algorithm.
protected boolean	step() Called to take a single step of the learning algorithm.

Methods inherited from class gov.sandia.cognition.learning.algorithm.AbstractAnytimeBatchLearner

clone, getData, getKeepGoing, learn, setData, setKeepGoing, stop

Methods inherited from class gov.sandia.cognition.algorithm.AbstractAnytimeAlgorithm

getMaxIterations, isResultValid, setMaxIterations

Methods inherited from class gov.sandia.cognition.algorithm.AbstractIterativeAlgorithm

addIterativeAlgorithmListener, fireAlgorithmEnded, fireAlgorithmStarted, fireStepEnded, fireStepStarted, getIteration, getListeners, removeIterativeAlgorithmListener, setIteration, setListeners

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface gov.sandia.cognition.learning.algorithm.BatchLearner

learn

Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable

clone

Methods inherited from interface gov.sandia.cognition.algorithm.AnytimeAlgorithm

getMaxIterations, setMaxIterations

Methods inherited from interface gov.sandia.cognition.algorithm.IterativeAlgorithm

addIterativeAlgorithmListener, getIteration, removeIterativeAlgorithmListener

Methods inherited from interface gov.sandia.cognition.algorithm.StoppableAlgorithm

isResultValid

Field Detail

DEFAULT_MAX_ITERATIONS

public static final int DEFAULT_MAX_ITERATIONS

The default maximum number of iterations is 100.

See Also:

Constant Field Values

weakLearner

protected BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>> weakLearner

The "weak learner" that must learn from the weighted input-output pairs on each iteration.

ensemble

protected transient WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>> ensemble

The ensemble learned by the algorithm.

weightedData

protected transient java.util.ArrayList<DefaultWeightedInputOutputPair<InputType,CategoryType>> weightedData

An array list containing the weighted version of the data.

Constructor Detail

MultiCategoryAdaBoost

public MultiCategoryAdaBoost()

Creates a new MultiCategoryAdaBoost with default parameters and a null weak learner.

MultiCategoryAdaBoost

public MultiCategoryAdaBoost(BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>> weakLearner,
                             int maxIterations)

Creates a new MultiCategoryAdaBoost with the given parameters.

Parameters:

weakLearner - The weak learner to use.

maxIterations - The maximum number of iterations. Must be positive.

Method Detail

initializeAlgorithm

protected boolean initializeAlgorithm()

Description copied from class: AbstractAnytimeBatchLearner

Called to initialize the learning algorithm's state based on the data that is stored in the data field. The return value indicates if the algorithm can be run or not based on the initialization.

Specified by:

initializeAlgorithm in class AbstractAnytimeBatchLearner<java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>

Returns:

True if the learning algorithm can be run and false if it cannot.

step

protected boolean step()

Description copied from class: AbstractAnytimeBatchLearner

Called to take a single step of the learning algorithm.

Specified by:

step in class AbstractAnytimeBatchLearner<java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>

Returns:

True if another step can be taken and false it the algorithm should halt.

cleanupAlgorithm

protected void cleanupAlgorithm()

Description copied from class: AbstractAnytimeBatchLearner

Called to clean up the learning algorithm's state after learning has finished.

Specified by:

cleanupAlgorithm in class AbstractAnytimeBatchLearner<java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>

getResult

public WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>> getResult()

Description copied from interface: AnytimeAlgorithm

Gets the current result of the algorithm.

Specified by:

getResult in interface AnytimeAlgorithm<WeightedVotingCategorizerEnsemble<InputType,CategoryType,Evaluator<? super InputType,? extends CategoryType>>>

Returns:

Current result of the algorithm.

getLearner

public BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>> getLearner()

Description copied from interface: BatchLearnerContainer

Gets the learner contained in this object.

Specified by:

getLearner in interface BatchLearnerContainer<BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>>>

Returns:

The learner contained in this object.

getWeakLearner

public BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>> getWeakLearner()

Gets the weak learner that is passed the weighted training data on each step of the algorithm.

Returns:

The weak learner for the algorithm to use.

setWeakLearner

public void setWeakLearner(BatchLearner<? super java.util.Collection<? extends InputOutputPair<? extends InputType,CategoryType>>,? extends Evaluator<? super InputType,? extends CategoryType>> weakLearner)

Sets the weak learner that is passed the weighted training data on each step of the algorithm.

Parameters:

weakLearner - The weak learner for the algorithm to use.