No description or website provided.
Latest commit 7687025 May 20, 2015 Wojciech Zaremba do gates in one go. Work by szagoruyko.

Test Plan:



Task ID: #

Blame Rev:

Long Short Term Memory Units

This is self-contained package to train a language model on word level Penn Tree Bank dataset. It achieves 115 perplexity for a small model in 1h, and 81 perplexity for a big model in a day. Model ensemble of 38 big models gives 69 perplexity. This code is derived from (the same author, but a different company).

More information: