Java Deep Learning Cookbook

How it works...

In step 2, word vectors from the trained model are saved to your local machine for further processing.

In step 3, we extracted data from all the unique word vectors by using WordVectorSerializer. Basically, this will load an in-memory VocabCache from the mentioned input words. But it doesn't load whole vocab/lookup tables into the memory, so it is capable of processing large vocabularies served over the network.

A VocabCache manages the storage of information required for the Word2Vec lookup table. We need to pass the labels to the t-SNE model, and labels are nothing but the words represented by word vectors.

In step 4, we created a list to add all unique words.

The BarnesHutTsne phrase is the DL4J implementation class for ...