org.deeplearning4j.models.embeddings.learning.impl.sequence

Class DBOW<T extends SequenceElement>

java.lang.Object

org.deeplearning4j.models.embeddings.learning.impl.sequence.DBOW<T>

All Implemented Interfaces:

SequenceLearningAlgorithm<T>

public class DBOW<T extends SequenceElement>
extends java.lang.Object
implements SequenceLearningAlgorithm<T>

Field Summary

Fields

Modifier and Type	Field and Description
protected VectorsConfiguration	configuration
protected WeightLookupTable<T>	lookupTable
protected double	negative
protected SkipGram<T>	skipGram
protected boolean	useAdaGrad
protected VocabCache<T>	vocabCache
protected int	window

Constructor Summary

Constructors

Constructor and Description
DBOW()

Method Summary

Modifier and Type	Method and Description
void	configure(VocabCache<T> vocabCache, WeightLookupTable<T> lookupTable, VectorsConfiguration configuration)
protected void	dbow(int i, Sequence<T> sequence, int b, java.util.concurrent.atomic.AtomicLong nextRandom, double alpha, boolean isInference, org.nd4j.linalg.api.ndarray.INDArray inferenceVector)
void	finish()
java.lang.String	getCodeName()
ElementsLearningAlgorithm<T>	getElementsLearningAlgorithm()
org.nd4j.linalg.api.ndarray.INDArray	inferSequence(Sequence<T> sequence, long nextRandom, double learningRate, double minLearningRate, int iterations) This method does training on previously unseen paragraph, and returns inferred vector
boolean	isEarlyTerminationHit() DBOW has no reasons for early termination
double	learnSequence(Sequence<T> sequence, java.util.concurrent.atomic.AtomicLong nextRandom, double learningRate) This method does training over the sequence of elements passed into it
void	pretrain(SequenceIterator<T> iterator) DBOW doesn't involves any pretraining

Methods inherited from class java.lang.Object

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

Field Detail

vocabCache

protected VocabCache<T extends SequenceElement> vocabCache

lookupTable

protected WeightLookupTable<T extends SequenceElement> lookupTable

configuration

protected VectorsConfiguration configuration

window

protected int window

useAdaGrad

protected boolean useAdaGrad

negative

protected double negative

skipGram

protected SkipGram<T extends SequenceElement> skipGram

Constructor Detail

DBOW

public DBOW()

Method Detail

getElementsLearningAlgorithm

public ElementsLearningAlgorithm<T> getElementsLearningAlgorithm()

Specified by:

getElementsLearningAlgorithm in interface SequenceLearningAlgorithm<T extends SequenceElement>

getCodeName

public java.lang.String getCodeName()

Specified by:

getCodeName in interface SequenceLearningAlgorithm<T extends SequenceElement>

configure

public void configure(@NonNull
                      VocabCache<T> vocabCache,
                      @NonNull
                      WeightLookupTable<T> lookupTable,
                      @NonNull
                      VectorsConfiguration configuration)

Specified by:

configure in interface SequenceLearningAlgorithm<T extends SequenceElement>

pretrain

public void pretrain(SequenceIterator<T> iterator)

DBOW doesn't involves any pretraining

Specified by:

pretrain in interface SequenceLearningAlgorithm<T extends SequenceElement>

Parameters:

iterator -

learnSequence

public double learnSequence(@NonNull
                            Sequence<T> sequence,
                            @NonNull
                            java.util.concurrent.atomic.AtomicLong nextRandom,
                            double learningRate)

Description copied from interface: SequenceLearningAlgorithm

This method does training over the sequence of elements passed into it

Specified by:

learnSequence in interface SequenceLearningAlgorithm<T extends SequenceElement>

Returns:

average score for this sequence

isEarlyTerminationHit

public boolean isEarlyTerminationHit()

DBOW has no reasons for early termination

Specified by:

isEarlyTerminationHit in interface SequenceLearningAlgorithm<T extends SequenceElement>

Returns:

dbow

protected void dbow(int i,
                    Sequence<T> sequence,
                    int b,
                    java.util.concurrent.atomic.AtomicLong nextRandom,
                    double alpha,
                    boolean isInference,
                    org.nd4j.linalg.api.ndarray.INDArray inferenceVector)

inferSequence

public org.nd4j.linalg.api.ndarray.INDArray inferSequence(Sequence<T> sequence,
                                                          long nextRandom,
                                                          double learningRate,
                                                          double minLearningRate,
                                                          int iterations)

This method does training on previously unseen paragraph, and returns inferred vector

Specified by:

inferSequence in interface SequenceLearningAlgorithm<T extends SequenceElement>

Parameters:

sequence -

nextRandom -

learningRate -

Returns:

finish

public void finish()

Specified by:

finish in interface SequenceLearningAlgorithm<T extends SequenceElement>