Deep Learning Study
Study of HeXA at Ulsan National Institute of Science and Technology.
Implementations
- DCGAN-tensorflow : Deep Convolutional GAN implementation in Tensorflow. [code] [demo]
- DQN-tensorflow :: Human-Level Control through Deep Reinforcement Learning implementation in Tensorflow. [code]
- MemN2N-tensorflow : End-To-End Memory Network implementation in Tensorflow. [code]
- NTM-tensorflow : Neural Turing Machine implementation in Tensorflow. [code]
- lstm-char-cnn-tensorflow : Character-Aware Neural Language Models implementation in Tensorflow. [code]
- visual-analogy-tensorflow : Deep Visual Analogy-Making implementation in Tensorflow. [code]
- variational-text-tensorflow : Neural Variational Inference for Text Processing in Tensorflow. [code]
- text-based-game-rl-tensorflow : Language Understanding for Text-based Games using Deep Reinforcement Learning implementation in Tensorflow. [code]
- neural-summary-tensorflow : Attention-Based Summarization implementation in TensorFlow. [code] (in progress)
- attentive-reader-tensorflow : Teaching Machines to Read and Comprehend implementation in TensorFlow. [code] (in progress)
Reasoning
Deep Reasoning presentation (3/17)
- [E2E MN] End-To-End Memory Networks [paper]
- Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus
- [E2E MN+] The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations [paper]
- Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston
- [DMN] Ask Me Anything: Dynamic Memory Networks for Natural Language Processing [paper]
- Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher
- [ReasoningNet] Towards Neural Network-based Reasoning [paper]
- Baolin Peng, Zhengdong Lu, Hang Li, Kam-Fai Wong
- [Impatient] Teaching Machines to Read and Comprehend [paper]
- Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom
- [Variational] Neural Variational Inference for Text Processing [paper]
- Yishu Miao, Lei Yu, Phil Blunsom
- [Attentive Pooling] Attentive Pooling Networks [paper]
- Cicero dos Santos, Ming Tan, Bing Xiang, Bowen Zhou
- [Attention Sum] Text Understanding with the Attention Sum Reader Network [paper]
- Rudolf Kadlec, Martin Schmid, Ondrej Bajgar, Jan Kleindienst
- [ABCNN] ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs [paper]
- Wenpeng Yin, Hinrich Schütze, Bing Xiang, Bowen Zhou
- [NTM] Empirical Study on Deep Learning Models for Question Answering [paper]
- Yang Yu, Wei Zhang, Chung-Wei Hang, Bing Xiang, Bowen Zhou
- [Dynamic] Learning to Compose Neural Networks for Question Answering [paper]
- Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein
Variational
- Auto-Encoding Variational Bayes [paper]
- Diederik P Kingma, Max Welling
- Generating Sentences from a Continuous Space [paper]
- Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio
- Neural Variational Inference for Text Processing [paper]
- Yishu Miao, Lei Yu, Phil Blunsom
- Learning Structured Output Representation using Deep Conditional Generative Models [paper]
- Kihyuk Sohn, Honglak Lee, Xinchen Yan
Learning Algorithm
- Neural GPUs Learn Algorithms [paper]
- Łukasz Kaiser, Ilya Sutskever
- Learning Efficient Algorithms with Hierarchical Attentive Memory [paper]
- Marcin Andrychowicz, Karol Kurach
- Neural Random-Access Machines [paper]
- Karol Kurach, Marcin Andrychowicz, Ilya Sutskever
- Neural Programmer: Inducing Latent Programs with Gradient Descent [paper]
- Arvind Neelakantan, Quoc V. Le, Ilya Sutskever
- Neural Programmer-Interpreters [paper]
- Scott Reed, Nando de Freitas
- Reinforcement Learning Neural Turing Machines [paper]
- Wojciech Zaremba, Ilya Sutskever
- Learning Simple Algorithms from Examples [paper]
- Wojciech Zaremba, Tomas Mikolov, Armand Joulin, Rob Fergus
Generative
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [paper]
- Alec Radford, Luke Metz, Soumith Chintala
- Deep Visual Analogy-Making [paper]
- Scott Reed, Yi Zhang, Yuting Zhang, Honglak Lee
- How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks [paper]
- Casper Kaae Sønderby, Tapani Raiko, Lars Maaløe, Søren Kaae Sønderby, Ole Winther
Natural Language Processing
- Exploring the Limits of Language Modeling [paper]
- Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, Yonghui Wu
- Swivel: Improving Embeddings by Noticing What's Missing [paper]
- Noam Shazeer, Ryan Doherty, Colin Evans, Chris Waterson
Reinforcement Learning
- Lie Access Neural Turing Machine [paper]
- Greg Yang
- Asynchronous Methods for Deep Reinforcement Learning [paper]
- Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu
ETC
- Learning Physical Intuition of Block Towers by Example [paper]
- Adam Lerer, Sam Gross, Rob Fergus