org.deeplearning4j.models.embeddings.learning

Interface SequenceLearningAlgorithm<T extends SequenceElement>

All Known Subinterfaces:

SparkSequenceLearningAlgorithm

All Known Implementing Classes:

BaseSparkSequenceLearningAlgorithm, DBOW, DM

public interface SequenceLearningAlgorithm<T extends SequenceElement>

Implementations of this interface should contain sequence-related learning algorithms. Like dbow or dm.

Method Summary

Modifier and Type	Method and Description
void	configure(VocabCache<T> vocabCache, WeightLookupTable<T> lookupTable, VectorsConfiguration configuration)
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()
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)

Method Detail

getCodeName

java.lang.String getCodeName()

configure

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

pretrain

void pretrain(SequenceIterator<T> iterator)

learnSequence

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

Parameters:

sequence -

nextRandom -

learningRate -

Returns:

average score for this sequence

isEarlyTerminationHit

boolean isEarlyTerminationHit()

inferSequence

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

Parameters:

sequence -

nextRandom -

learningRate -

Returns:

getElementsLearningAlgorithm

ElementsLearningAlgorithm<T> getElementsLearningAlgorithm()

finish

void finish()