├── 1_reasoning.pdf └── README.md /1_reasoning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/carpedm20/deep-learning-study/75a2cbcb93e45eb60a3b5646eebedd02cd328701/1_reasoning.pdf -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | Deep Learning Study 2 | =================== 3 | 4 | Study of HeXA at Ulsan National Institute of Science and Technology. 5 | 6 | 7 | Implementations 8 | --------------- 9 | 10 | - **DCGAN-tensorflow** : [Deep Convolutional GAN](http://arxiv.org/abs/1511.06434v1) implementation in Tensorflow. [[code](https://github.com/carpedm20/DCGAN-tensorflow)] [[demo](http://carpedm20.github.io/faces/)] 11 | - **DQN-tensorflow** :: [Human-Level Control through Deep Reinforcement Learning](http://home.uchicago.edu/~arij/journalclub/papers/2015_Mnih_et_al.pdf) implementation in Tensorflow. [[code](https://github.com/devsisters/DQN-tensorflow/)] 12 | - **MemN2N-tensorflow** : [End-To-End Memory Network](http://arxiv.org/abs/1503.08895v4) implementation in Tensorflow. [[code](https://github.com/carpedm20/MemN2N-tensorflow)] 13 | - **NTM-tensorflow** : [Neural Turing Machine](http://arxiv.org/abs/1410.5401) implementation in Tensorflow. [[code](https://github.com/carpedm20/NTM-tensorflow)] 14 | - lstm-char-cnn-tensorflow : [Character-Aware Neural Language Models](http://arxiv.org/abs/1508.06615) implementation in Tensorflow. [[code](https://github.com/carpedm20/lstm-char-cnn-tensorflow)] 15 | - **visual-analogy-tensorflow** : [Deep Visual Analogy-Making](http://www-personal.umich.edu/~reedscot/nips2015.pdf) implementation in Tensorflow. [[code](https://github.com/carpedm20/visual-analogy-tensorflow)] 16 | - variational-text-tensorflow : [Neural Variational Inference for Text Processing](http://arxiv.org/abs/1511.06038) in Tensorflow. [[code](https://github.com/carpedm20/variational-text-tensorflow)] 17 | - text-based-game-rl-tensorflow : [Language Understanding for Text-based Games using Deep Reinforcement Learning](http://arxiv.org/abs/1506.08941) implementation in Tensorflow. [[code](https://github.com/carpedm20/text-based-game-rl-tensorflow)] 18 | - neural-summary-tensorflow : [Attention-Based Summarization](http://arxiv.org/abs/1509.00685) implementation in TensorFlow. [[code](https://github.com/carpedm20/neural-summary-tensorflow)] \(*in progress*\) 19 | - attentive-reader-tensorflow : [Teaching Machines to Read and Comprehend](http://arxiv.org/abs/1506.03340v3) implementation in TensorFlow. [[code](https://github.com/carpedm20/attentive-reader-tensorflow)] \(*in progress*\) 20 | 21 | 22 | Reasoning 23 | -------- 24 | 25 | [Deep Reasoning presentation](./1_reasoning.pdf) (3/17) 26 | 27 | - [E2E MN] End-To-End Memory Networks [[paper](http://arxiv.org/abs/1503.08895)] 28 | - Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus 29 | - [E2E MN+] The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations [[paper](http://arxiv.org/abs/1511.02301)] 30 | - Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston 31 | - [DMN] Ask Me Anything: Dynamic Memory Networks for Natural Language Processing [[paper](http://arxiv.org/abs/1506.07285)] 32 | - Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher 33 | - [ReasoningNet] Towards Neural Network-based Reasoning [[paper](http://arxiv.org/abs/1508.05508)] 34 | - Baolin Peng, Zhengdong Lu, Hang Li, Kam-Fai Wong 35 | - [Impatient] Teaching Machines to Read and Comprehend [[paper](http://arxiv.org/abs/1506.03340)] 36 | - Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom 37 | - [Variational] Neural Variational Inference for Text Processing [[paper](http://arxiv.org/abs/1511.06038)] 38 | - Yishu Miao, Lei Yu, Phil Blunsom 39 | - [Attentive Pooling] Attentive Pooling Networks [[paper](http://arxiv.org/abs/1602.03609)] 40 | - Cicero dos Santos, Ming Tan, Bing Xiang, Bowen Zhou 41 | - [Attention Sum] Text Understanding with the Attention Sum Reader Network [[paper](http://arxiv.org/abs/1603.01547)] 42 | - Rudolf Kadlec, Martin Schmid, Ondrej Bajgar, Jan Kleindienst 43 | - [ABCNN] ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs [[paper](http://arxiv.org/abs/1512.05193)] 44 | - Wenpeng Yin, Hinrich Schütze, Bing Xiang, Bowen Zhou 45 | - [NTM] Empirical Study on Deep Learning Models for Question Answering [[paper](http://arxiv.org/abs/1510.07526)] 46 | - Yang Yu, Wei Zhang, Chung-Wei Hang, Bing Xiang, Bowen Zhou 47 | - [Dynamic] Learning to Compose Neural Networks for Question Answering [[paper](http://arxiv.org/abs/1601.01705)] 48 | - Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein 49 | 50 | 51 | Variational 52 | ----------- 53 | 54 | - Auto-Encoding Variational Bayes [[paper](http://arxiv.org/abs/1312.6114)] 55 | - Diederik P Kingma, Max Welling 56 | - Generating Sentences from a Continuous Space [[paper](http://arxiv.org/abs/1511.06349)] 57 | - Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio 58 | - Neural Variational Inference for Text Processing [[paper](http://arxiv.org/abs/1511.06038)] 59 | - Yishu Miao, Lei Yu, Phil Blunsom 60 | - Learning Structured Output Representation using Deep Conditional Generative Models [[paper](http://papers.nips.cc/paper/5775-learning-structured-output-representation-using-deep-conditional-generative-models)] 61 | - Kihyuk Sohn, Honglak Lee, Xinchen Yan 62 | 63 | 64 | Learning Algorithm 65 | ------------------ 66 | 67 | - Neural GPUs Learn Algorithms [[paper](http://arxiv.org/abs/1511.08228)] 68 | - Łukasz Kaiser, Ilya Sutskever 69 | - Learning Efficient Algorithms with Hierarchical Attentive Memory [[paper](http://arxiv.org/abs/1602.03218)] 70 | - Marcin Andrychowicz, Karol Kurach 71 | - Neural Random-Access Machines [[paper](http://arxiv.org/abs/1511.06392)] 72 | - Karol Kurach, Marcin Andrychowicz, Ilya Sutskever 73 | - Neural Programmer: Inducing Latent Programs with Gradient Descent [[paper](http://arxiv.org/abs/1511.04834)] 74 | - Arvind Neelakantan, Quoc V. Le, Ilya Sutskever 75 | - Neural Programmer-Interpreters [[paper](http://arxiv.org/abs/1511.06279)] 76 | - Scott Reed, Nando de Freitas 77 | - Reinforcement Learning Neural Turing Machines [[paper](http://arxiv.org/abs/1505.00521)] 78 | - Wojciech Zaremba, Ilya Sutskever 79 | - Learning Simple Algorithms from Examples [[paper](http://arxiv.org/abs/1511.07275)] 80 | - Wojciech Zaremba, Tomas Mikolov, Armand Joulin, Rob Fergus 81 | 82 | 83 | Generative 84 | ---------- 85 | 86 | - Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [[paper](http://arxiv.org/abs/1511.06434)] 87 | - Alec Radford, Luke Metz, Soumith Chintala 88 | - Deep Visual Analogy-Making [[paper](http://www-personal.umich.edu/~reedscot/nips2015.pdf)] 89 | - Scott Reed, Yi Zhang, Yuting Zhang, Honglak Lee 90 | - How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks [[paper](http://arxiv.org/abs/1602.02282)] 91 | - Casper Kaae Sønderby, Tapani Raiko, Lars Maaløe, Søren Kaae Sønderby, Ole Winther 92 | 93 | 94 | 95 | Natural Language Processing 96 | --------------------------- 97 | 98 | - Exploring the Limits of Language Modeling [[paper](http://arxiv.org/abs/1602.02410)] 99 | - Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, Yonghui Wu 100 | - Swivel: Improving Embeddings by Noticing What's Missing [[paper](http://arxiv.org/abs/1602.02215)] 101 | - Noam Shazeer, Ryan Doherty, Colin Evans, Chris Waterson 102 | 103 | 104 | Reinforcement Learning 105 | ---------------------- 106 | 107 | - Lie Access Neural Turing Machine [[paper](http://arxiv.org/abs/1602.08671)] 108 | - Greg Yang 109 | - Asynchronous Methods for Deep Reinforcement Learning [[paper](http://arxiv.org/abs/1602.01783)] 110 | - Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu 111 | 112 | 113 | ETC 114 | --- 115 | 116 | - Learning Physical Intuition of Block Towers by Example [[paper](http://arxiv.org/abs/1603.01312)] 117 | - Adam Lerer, Sam Gross, Rob Fergus 118 | 119 | 120 | Links 121 | ----- 122 | 123 | - [papernote](https://github.com/dennybritz/deeplearning-papernotes) 124 | --------------------------------------------------------------------------------