Understanding building blocks of ULMFIT
ML Review
FEBRUARY 11, 2019
In the original AWD-LSTM paper authors emphasize on how dataset usage in traditional language modeling is inefficient. Still there is one more encoder layer that you might consider instead of LSTM, QRNN — Quasi-Recurrent Neural Network, a work from some of the same authors from AWD-LSTM.
52 
Let's personalize your content