awesome-rnn

Python, C++

,

Tutorials

by nlintz

Notebook examples

by aymericdamien

Scikit Flow (skflow)

Simplified Scikit-learn like Interface for TensorFlow

: (Tensorflow / Theano)-based modular deep learning library similar to Torch

char-rnn-tensorflow

by sherjilozair: char-rnn in tensorflow

Python

Simple IPython

: Library that wraps a lot of models and training algorithms in deep learning

Blocks

: modular framework that enables building neural network models

: (Tensorflow / Theano)-based modular deep learning library similar to Torch

Lasagne

: Lightweight library to build and train neural networks in Theano

theano-rnn

by Graham Taylor

Passage

: Library for text analysis with RNNs

Theano-Lights

: Contains many generative models

Caffe

C++ with MATLAB/Python wrappers

by Jeff Donahue

Lua

torchnet

: modular framework that enables building neural network models

char-rnn

by Andrej Karpathy : multi-layer RNN/LSTM/GRU for training/sampling from character-level language models

torch-rnn

by Justin Johnson : reusable RNN/LSTM modules for torch7 - much faster and memory efficient reimplementation of char-rnn

neuraltalk2

by Andrej Karpathy : Recurrent Neural Network captions image, much faster and better version of the original

LSTM

by Wojciech Zaremba : Long Short Term Memory Units to train a language model on word level Penn Tree Bank dataset

by Nando de Freitas : Oxford Computer Science - Machine Learning 2015 Practicals

rnn

by Nicholas Leonard : general library for implementing RNN, LSTM, BRNN and BLSTM (highly unit tested)

Python

Word-level RNN example

: demonstrates PyTorch's built in RNN modules for language modeling

Practical PyTorch tutorials

by Sean Robertson : focuses on using RNNs for Natural Language Processing

Deep Learning For NLP In PyTorch

by Robert Guthrie : written for a Natural Language Processing class at Georgia Tech

by : Deep Learning library for Java, Scala & Clojure on Hadoop, Spark & GPUs

(Also in , , ) : ,

: new deep learning library in Python, with support for RNN/LSTM, and a fast image captioning model

Brainstorm

: deep learning library in Python, developed by IDSIA, thereby including various recurrent structures

: new, flexible deep learning library in Python

(Computational Graph Toolkit) : replicates Theano's API, but with very short compilation time and multithreading

by Alex Graves : C++ based LSTM library

by Tomas Mikolov : C++ based simple code

faster-RNNLM

of Yandex : C++ based rnnlm implementation aimed to handle huge datasets

neuraltalk

by Andrej Karpathy : numpy-based RNN/LSTM implementation

by Andrej Karpathy : raw numpy code that implements an efficient batched LSTM

Recurrentjs

by Andrej Karpathy : a beta javascript library for RNN

DARQN

by 5vision : Deep Attention Recurrent Q-Network

Stanford NLP ( ) by Richard Socher

: neural network basics

: RNN language models, bi-directional RNN, GRU, LSTM

Stanford vision ( ) by Andrej Karpathy

Oxford by Nando de Freitas

: Recurrent neural networks and LSTMs

: (guest lecture) Alex Graves on Hallucination with RNNs

Bi-directional RNN [ ]

Multi-dimensional RNN [ ]

GFRNN [ ] [ ] [ ]

Kai Sheng Tai, Richard Socher, and Christopher D. Manning, , arXiv:1503.00075 / ACL 2015 [ ]

Samuel R. Bowman, Christopher D. Manning, and Christopher Potts, , arXiv:1506.04834 [ ]

Grid LSTM [ ] [ ]

Segmental RNN [ ]

Seq2seq for Sets [ ]

Hierarchical Recurrent Neural Networks [ ]

LSTM [ ]

GRU (Gated Recurrent Unit) [ ]

NTM [ ]

Neural GPU [ ]

Memory Network [ ]

Pointer Network [ ]

Deep Attention Recurrent Q-Network [ ]

Dynamic Memory Networks [ ]

Yann LeCun, Yoshua Bengio, and Geoffrey Hinton, , Nature 2015

Klaus Greff, Rupesh Kumar Srivastava, Jan Koutnik, Bas R. Steunebrink, Jurgen Schmidhuber, , arXiv:1503.04069

Zachary C. Lipton, , arXiv:1506.00019

Andrej Karpathy, Justin Johnson, Li Fei-Fei, , arXiv:1506.02078

Rafal Jozefowicz, Wojciech Zaremba, Ilya Sutskever, , ICML, 2015

Tomas Mikolov, Martin Karafiat, Lukas Burget, Jan "Honza" Cernocky, Sanjeev Khudanpur, , Interspeech 2010 [ ]

Tomas Mikolov, Stefan Kombrink, Lukas Burget, Jan "Honza" Cernocky, Sanjeev Khudanpur, , ICASSP 2011 [ ]

Stefan Kombrink, Tomas Mikolov, Martin Karafiat, Lukas Burget, , Interspeech 2011 [ ]

Jiwei Li, Minh-Thang Luong, and Dan Jurafsky, , ACL 2015 [ ], [ ]

Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, and Richard S. Zemel, , arXiv:1506.06726 / NIPS 2015 [ ]

Yoon Kim, Yacine Jernite, David Sontag, and Alexander M. Rush, , arXiv:1508.06615 [ ]

Xingxing Zhang, Liang Lu, and Mirella Lapata, , arXiv:1511.00060 [ ]

Felix Hill, Antoine Bordes, Sumit Chopra, and Jason Weston, , arXiv:1511.0230 [ ]

Geoffrey Hinton, Li Deng, Dong Yu, George E. Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N. Sainath, and Brian Kingsbury, , IEEE Signam Processing Magazine 2012 [ ]

Alex Graves, Abdel-rahman Mohamed, and Geoffrey Hinton, , arXiv:1303.5778 / ICASSP 2013 [ ]

Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk, Kyunghyun Cho, and Yoshua Bengio, , arXiv:1506.07503 / NIPS 2015 [ ]

Haşim Sak, Andrew Senior, Kanishka Rao, and Françoise Beaufays. , arXiv:1507.06947 2015 [ ]

Oxford [ ]

Kyunghyun Cho, Bart van Berrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio, , arXiv:1406.1078 / EMNLP 2014 [ ]

Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, and Yoshua Bengio, , SSST-8 2014 [ ]

Dzmitry Bahdanau, KyungHyun Cho, and Yoshua Bengio, , arXiv:1409.0473 / ICLR 2015 [ ]

Sebastian Jean, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio, , arXiv:1412.2007 / ACL 2015 [ ]

Univ. Montreal + Middle East Tech. Univ. + Univ. Maine [ ]

Google [ ]

Google + NYU [ ]

ICT + Huawei [ ]

Stanford [ ]

Middle East Tech. Univ. + NYU + Univ. Montreal [ ]

Lifeng Shang, Zhengdong Lu, and Hang Li, , arXiv:1503.02364 / ACL 2015 [ ]

Oriol Vinyals and Quoc V. Le, , arXiv:1506.05869 [ ]

Ryan Lowe, Nissan Pow, Iulian V. Serban, and Joelle Pineau, , arXiv:1506.08909 [ ]

Jesse Dodge, Andreea Gane, Xiang Zhang, Antoine Bordes, Sumit Chopra, Alexander Miller, Arthur Szlam, and Jason Weston, , arXiv:1511.06931 [ ]

Jason Weston, , arXiv:1604.06045, [ ]

Antoine Bordes and Jason Weston, , arXiv:1605.07683 [ ]

Jason Weston, Antoine Bordes, Sumit Chopra, Tomas Mikolov, and Alexander M. Rush, , arXiv:1502.05698 [ ] [ ]

Antoine Bordes, Nicolas Usunier, Sumit Chopra, and Jason Weston, , arXiv:1506.02075 [ ]

Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston, "The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations", ICLR 2016 [ ]

DeepMind + Oxford [ ]

MetaMind [ ]

Pedro Pinheiro and Ronan Collobert, , ICML 2014 [ ]

Ming Liang and Xiaolin Hu, , CVPR 2015 [ ]

Wonmin Byeon, Thomas Breuel, Federico Raue1, and Marcus Liwicki1, , CVPR 2015 [ ]

Mircea Serban Pavel, Hannes Schulz, and Sven Behnke, , IJCNN 2015 [ ]

Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet, Zhizhong Su, Dalong Du, Chang Huang, and Philip H. S. Torr, , arXiv:1502.03240 [ ]

Xiaodan Liang, Xiaohui Shen, Donglai Xiang, Jiashi Feng, Liang Lin, and Shuicheng Yan, , arXiv:1511.04510 [ ]

Sean Bell, C. Lawrence Zitnick, Kavita Bala, and Ross Girshick, , arXiv:1512.04143 / ICCV 2015 workshop [ ]

Quan Gan, Qipeng Guo, Zheng Zhang, and Kyunghyun Cho, , arXiv:1511.06425 [ ]

Karol Gregor, Ivo Danihelka, Alex Graves, Danilo J. Rezende, and Daan Wierstra, ICML 2015 [ ]

Angeliki Lazaridou, Dat T. Nguyen, R. Bernardi, and M. Baroni, arXiv:1506.03500 [ ]

Lucas Theis and Matthias Bethge, arXiv:1506.03478 / NIPS 2015 [ ]

Aaron van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu, arXiv:1601.06759 [ ]

Univ. Toronto [ ]

Univ. Cambridge [ ]

UCLA + Baidu [ ] [ ], [ ]

Univ. Toronto [ ] [ ]

Berkeley [ ] [ ]

Google [ ]

Stanford

Microsoft [ ]

CMU + Microsoft [ ], [ ]

Univ. Montreal + Univ. Toronto [ ] [ ]

Idiap + EPFL + Facebook [ ]

UCLA + Baidu [ ]

Jacob Devlin, Saurabh Gupta, Ross Girshick, Margaret Mitchell, and C. Lawrence Zitnick, , arXiv:1505.04467 (Note: technically not RNN) [ ]

Jacob Devlin, Hao Cheng, Hao Fang, Saurabh Gupta, Li Deng, Xiaodong He, Geoffrey Zweig, and Margaret Mitchell, , arXiv:1505.01809 [ ]

Adelaide [ ]

Tilburg [ ]

Univ. Montreal [ ]

Cornell [ ]

Berkeley [ ] [ ]

UT Austin + UML + Berkeley [ ]

Microsoft [ ]

UT Austin + Berkeley + UML [ ]

Univ. Montreal + Univ. Sherbrooke [ ]

MPI + Berkeley [ ]

Univ. Toronto + MIT [ ]

Univ. Montreal [ ]

Zhejiang Univ. + UTS [ ]

Univ. Montreal + NYU + IBM [ ]

Virginia Tech. + MSR [ ] [ ]

MPI + Berkeley [ ] [ ]

Univ. Toronto [ ] [ ]

Baidu + UCLA [ ] [ ]

SNU + NAVER [ ]

UC Berkeley + Sony [ ]

Postech [ ]

SNU + NAVER [ ]

CMU + UTS [ ]

KIT + MIT + Univ. Toronto [ ] [ ]

A.Graves, G. Wayne, and I. Danihelka., arXiv preprint arXiv:1410.5401 [ ]

Jason Weston, Sumit Chopra, Antoine Bordes, arXiv:1410.3916 [ ]

Armand Joulin and Tomas Mikolov, , arXiv:1503.01007 / NIPS 2015 [ ]

Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus, , arXiv:1503.08895 / NIPS 2015 [ ]

Wojciech Zaremba and Ilya Sutskever, arXiv:1505.00521 [ ]

Baolin Peng and Kaisheng Yao, , arXiv:1506.00195 [ ]

Fandong Meng, Zhengdong Lu, Zhaopeng Tu, Hang Li, and Qun Liu, , arXiv:1506.06442 [ ]

Arvind Neelakantan, Quoc V. Le, and Ilya Sutskever, , arXiv:1511.04834 [ ]

Scott Reed and Nando de Freitas, , arXiv:1511.06279 [ ]

Karol Kurach, Marcin Andrychowicz, and Ilya Sutskever, , arXiv:1511.06392 [ ]

Łukasz Kaiser and Ilya Sutskever, , arXiv:1511.08228 [ ]

Ethan Caballero, , arXiv:1511.6420 [ ]

Wojciech Zaremba, Tomas Mikolov, Armand Joulin, and Rob Fergus, , arXiv:1511.07275 [ ]

Hongyuan Mei, Mohit Bansal, and Matthew R. Walter, , arXiv:1506.04089 [ ]

Marvin Zhang, Sergey Levine, Zoe McCarthy, Chelsea Finn, and Pieter Abbeel, arXiv:1507.01273

Alex Graves, arXiv:1308.0850

Volodymyr Mnih, Nicolas Heess, Alex Graves, and Koray Kavukcuoglu, , NIPS 2014 / arXiv:1406.6247 [ ]

Wojciech Zaremba and Ilya Sutskever, , arXiv:1410.4615 [ ] [ ]

Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer, , arXiv:1506.03099 / NIPS 2015 [ ]

Bing Shuai, Zhen Zuo, Gang Wang, and Bing Wang, , arXiv:1509.00552 [ ]

Soren Kaae Sonderby, Casper Kaae Sonderby, Lars Maaloe, and Ole Winther, , arXiv:1509.05329 [ ]

Cesar Laurent, Gabriel Pereyra, Philemon Brakel, Ying Zhang, and Yoshua Bengio, , arXiv:1510.01378 [ ]

Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee, , arXiv:1511.04491

Quan Gan, Qipeng Guo, Zheng Zhang, and Kyunghyun Cho, , arXiv:1511.06425 [ ]

Francesco Visin, Kyle Kastner, Aaron Courville, Yoshua Bengio, Matteo Matteucci, and Kyunghyun Cho, , arXiv:1511.07053 [ ]

Juergen Schmidhuber, , arXiv:1511.09249

(Open Speech and Language Resources)

Dataset for text understanding and reasoning, by Facebook AI Research. Contains:

The (20) QA bAbI tasks - [ ]

The (6) dialog bAbI tasks - [ ]

The Children's Book Test - [ ]

The Movie Dialog dataset - [ ]

The MovieQA dataset - [ ]

The Dialog-based Language Learning dataset - [ ]

The SimpleQuestions dataset - [ ]

Stanford Question Answering Dataset : [ ]

built upon by N. Silberman et al

based on images

based on MSCOCO images

built from scratch by Baidu - in Chinese, with English translation

: Large-scale action recognition dataset

: Extension of THUMOS '14 action detection dataset with dense multilabele annotation

by

in

blog's RNN tutorial [ ], [ ], [ ], [ ]

from Baidu's Silicon Valley AI Lab

by Yoav Goldberg

by Danijar Hafner

by Danijar Hafner

by Silviu Pitis

Alex graves, hand-writing generation [ ]

Ink Poster: Handwritten post-it notes [ ]

LSTMVis: Visual Analysis for Recurrent Neural Networks [ ]