Created by agibsonccc on 10/19/14.
Huffman tree builder
This is special limited Word2Vec implementation, suited for serving as lookup table in concurrent multi-gpu environment This implementation DOES NOT load all vectors onto any of gpus, instead of that it holds vectors in, optionally, compressed state in host memory.
Intermediate layers of the neural network
Vocab work meant for use with the vocab actor
This is Word2Vec implementation based on SequenceVectors