Library for implementing RNNs with Theano
Switch branches/tags
Clone or download
kyunghyuncho Merge pull request #7 from mkudinov/feature-bugfix-implicit-casting
Bugfix: implicit casting int64 + float32 used to cause a type error. Cas...
Latest commit 3691cbf Oct 22, 2014
Type Name Latest commit message Commit time
Failed to load latest commit information.
doc basic intro to RNN Mar 21, 2014
groundhog Bugfix: implicit casting int64 + float32 used to cause a type error. … Oct 21, 2014
scripts bug in handling decoder recurrent parameters fixed Jun 17, 2014
.gitignore to ignore Jan 22, 2014
LICENSE Initial commit Jan 14, 2014 RNN Encoder-Decoder Experiment Script Jun 4, 2014


This library is built on top of Theano ( and can be used with Jobman ( It is meant to provide a flexible yet efficient way of implementing complex recurrent models. Currently it supports variations of recurrent neural networks (such as DT-RNN, DOT-RNN, RNN Encoder-Decoder) and stacked version of them.

Most of the library documentation is still work in progress, but check the files containing Tut (in scripts) for a quick tutorial on how to use the library.

The library was developed at University of Montreal, in Lisa lab (\_en.html). Among the main contributors are Razvan Pascanu, KyungHyun Cho and Caglar Gulcehre.

The library is under the 3-clause BSD license, so it may be used for commercial purposes.