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 Object
implements SequenceLearningAlgorithm<T>

Author:

[email protected]

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, AtomicLong nextRandom, double alpha)
String	getCodeName()
boolean	isEarlyTerminationHit() DBOW has no reasons for early termination
double	learnSequence(Sequence<T> sequence, 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

getCodeName

public 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
                            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,
                    AtomicLong nextRandom,
                    double alpha)