Uses of Class
org.deeplearning4j.spark.models.embeddings.word2vec.Word2Vec.Builder

Packages that use Word2Vec.Builder

Package	Description
org.deeplearning4j.spark.models.embeddings.word2vec

Uses of Word2Vec.Builder in org.deeplearning4j.spark.models.embeddings.word2vec

Methods in org.deeplearning4j.spark.models.embeddings.word2vec that return Word2Vec.Builder

Modifier and Type	Method and Description
Word2Vec.Builder	Word2Vec.Builder.batchSize(int batchSize) Specifies the size of mini-batch, used in single iteration during training
Word2Vec.Builder	Word2Vec.Builder.epochs(int numEpochs) This method specifies number of epochs done over whole corpus PLEASE NOTE: NOT IMPLEMENTED
Word2Vec.Builder	Word2Vec.Builder.iterations(int numIterations) This method specifies number of iterations over batch on each node
Word2Vec.Builder	Word2Vec.Builder.layerSize(int layerSize) Specifies output vector's dimensions
Word2Vec.Builder	Word2Vec.Builder.learningRate(double lr) This method specifies initial learning rate for model
Word2Vec.Builder	Word2Vec.Builder.minLearningRate(double mlr) This method specifies bottom threshold for learning rate decay
Word2Vec.Builder	Word2Vec.Builder.minWordFrequency(int minWordFrequency) This method specifies minimum word frequency threshold.
Word2Vec.Builder	Word2Vec.Builder.negative(int negative) Specifies negative sampling
Word2Vec.Builder	Word2Vec.Builder.sampling(double sampling) Specifies subsamplng value
Word2Vec.Builder	Word2Vec.Builder.seed(long seed) Specifies random seed to be used during weights initialization;
Word2Vec.Builder	Word2Vec.Builder.setNGrams(int nGrams) Specifies N of n-Grams :)
Word2Vec.Builder	Word2Vec.Builder.stopWords(List<String> stopWords) This method defines list of stop-words, that are to be ignored during vocab building and training
Word2Vec.Builder	Word2Vec.Builder.tokenizerFactory(String tokenizer) Specifies TokenizerFactory class to be used for tokenization
Word2Vec.Builder	Word2Vec.Builder.tokenizerFactory(TokenizerFactory factory) Specifies TokenizerFactory to be used for tokenization PLEASE NOTE: You can't use anonymous implementation here
Word2Vec.Builder	Word2Vec.Builder.tokenPreprocessor(String tokenPreprocessor) Specifies TokenPreProcessor class to be used during tokenization
Word2Vec.Builder	Word2Vec.Builder.useAdaGrad(boolean reallyUse) This method specifies, if adaptive gradients should be used during model training
Word2Vec.Builder	Word2Vec.Builder.useUnknown(boolean reallyUse) Specifies, if UNK word should be used instead of words that are absent in vocab
Word2Vec.Builder	Word2Vec.Builder.windowSize(int windowSize) Specifies window size