org.deeplearning4j.models.embeddings.learning.impl.elements

Class SkipGram<T extends SequenceElement>

java.lang.Object

org.deeplearning4j.models.embeddings.learning.impl.elements.SkipGram<T>

All Implemented Interfaces:

ElementsLearningAlgorithm<T>

public class SkipGram<T extends SequenceElement>
extends Object
implements ElementsLearningAlgorithm<T>

Skip-Gram implementation for dl4j SequenceVectors

Author:

[email protected]

Field Summary

Fields

Modifier and Type	Field and Description
protected VectorsConfiguration	configuration
protected double[]	expTable
protected WeightLookupTable<T>	lookupTable
protected static double	MAX_EXP
protected double	negative
protected double	sampling
protected org.nd4j.linalg.api.ndarray.INDArray	syn0
protected org.nd4j.linalg.api.ndarray.INDArray	syn1
protected org.nd4j.linalg.api.ndarray.INDArray	syn1Neg
protected org.nd4j.linalg.api.ndarray.INDArray	table
protected boolean	useAdaGrad
protected VocabCache<T>	vocabCache
protected int	window

Constructor Summary

Constructors

Constructor and Description
SkipGram() Dummy construction is required for reflection

Method Summary

Modifier and Type	Method and Description
Sequence<T>	applySubsampling(Sequence<T> sequence, AtomicLong nextRandom)
void	configure(VocabCache<T> vocabCache, WeightLookupTable<T> lookupTable, VectorsConfiguration configuration) SkipGram initialization over given vocabulary and WeightLookupTable
String	getCodeName() Returns implementation code name
boolean	isEarlyTerminationHit() SkipGram has no reasons for early termination ever.
double	iterateSample(T w1, T w2, AtomicLong nextRandom, double alpha)
double	learnSequence(Sequence<T> sequence, AtomicLong nextRandom, double learningRate) Learns sequence using SkipGram algorithm
void	pretrain(SequenceIterator<T> iterator) SkipGram 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

MAX_EXP

protected static double MAX_EXP

expTable

protected double[] expTable

window

protected int window

useAdaGrad

protected boolean useAdaGrad

negative

protected double negative

sampling

protected double sampling

syn0

protected org.nd4j.linalg.api.ndarray.INDArray syn0

syn1

protected org.nd4j.linalg.api.ndarray.INDArray syn1

syn1Neg

protected org.nd4j.linalg.api.ndarray.INDArray syn1Neg

table

protected org.nd4j.linalg.api.ndarray.INDArray table

Constructor Detail

SkipGram

public SkipGram()

Dummy construction is required for reflection

Method Detail

getCodeName

public String getCodeName()

Returns implementation code name

Specified by:

getCodeName in interface ElementsLearningAlgorithm<T extends SequenceElement>

Returns:

configure

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

SkipGram initialization over given vocabulary and WeightLookupTable

Specified by:

configure in interface ElementsLearningAlgorithm<T extends SequenceElement>

Parameters:

vocabCache -

lookupTable -

configuration -

pretrain

public void pretrain(SequenceIterator<T> iterator)

SkipGram doesn't involves any pretraining

Specified by:

pretrain in interface ElementsLearningAlgorithm<T extends SequenceElement>

Parameters:

iterator -

applySubsampling

public Sequence<T> applySubsampling(@NonNull
                                    Sequence<T> sequence,
                                    @NonNull
                                    AtomicLong nextRandom)

learnSequence

public double learnSequence(@NonNull
                            Sequence<T> sequence,
                            @NonNull
                            AtomicLong nextRandom,
                            @NonNull
                            double learningRate)

Learns sequence using SkipGram algorithm

Specified by:

learnSequence in interface ElementsLearningAlgorithm<T extends SequenceElement>

Parameters:

sequence -

nextRandom -

learningRate -

Returns:

average score for this sequence

isEarlyTerminationHit

public boolean isEarlyTerminationHit()

SkipGram has no reasons for early termination ever.

Specified by:

isEarlyTerminationHit in interface ElementsLearningAlgorithm<T extends SequenceElement>

Returns:

iterateSample

public double iterateSample(T w1,
                            T w2,
                            AtomicLong nextRandom,
                            double alpha)