laulysta's repositories
nmt_transformer
Transformer model in Pytorch
recurent_autoencoder_temp_model
We want to force temporal models, like LSTM and GRU, to have better representation of the past (better memory). We do this by reconstructing the previous hidden representations using autoencoders.
laulysta.github.io
My web page
LSTM_baseline
Simple LSTM baseline (with GRU and RNN option) for the DocNADE paper.
nmt_pytorch
Neural Machine Translation model in pytorch
qsubLauncher_NYU
Development of a command that launch job on the Mercer cluster.
smartdispatch
An easy to use job launcher for supercomputers with PBS compatible job manager.
tensor2tensor
A library for generalized sequence to sequence models