Papers

Summaries of papers on deep learning.

2018

• World Models [Paper] [Review]
  • David Ha, Jürgen Schmidhuber, ArXiv, 2018

2017

• A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment [Paper] [Review]
  • Haonan Yu, Haichao Zhang, Wei Xu, ArXiv, 2017
• A simple neural network module for relational reasoning [Paper] [Review]
  • Adam Santoro, David Raposo, David G.T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, Timothy Lillicrap, NIPS, 2017
• Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning [Paper] [Review]
  • Qi Wu, Peng Wang, Chunhua Shen, Ian Reid, Anton van den Hengel, ArXiv, 2017
• From Red Wine to Red Tomato: Composition with Context [Paper] [Review]
  • Ishan Misra, Abhinav Gupta, Martial Hebert, CVPR, 2017
• Towards Diverse and Natural Image Descriptions via a Conditional GAN [Paper] [Review]
  • Bo Dai, Sanja Fidler, Raquel Urtasun, Dahua Lin, ICCV, 2017

2016

• Actions ~ Transformations [Paper] [Review]
  • Xiaolong Wang, Ali Farhadi, Abhinav Gupta, CVPR, 2016
• Building Machines That Learn and Think Like People [Paper] [Review]
  • Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman, Behavioral and Brain Sciences, 2016
• Deep Compositional Question Answering with Neural Module Networks [Paper] [Review]
  • Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein, CVPR, 2016
• Deep Networks with Stochastic Depth [Paper] [Review]
  • Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, Kilian Weinberger, ArXiv, 2016
• Deep Reinforcement Learning for Dialogue Generation [Paper] [Review]
  • Jiwei Li, Will Monroe, Alan Ritter, Michel Galley, Jianfeng Gao, Dan Jurafsky, ArXiv, 2016
• Deep Residual Learning for Image Recognition [Paper] [Review]
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, ArXiv, 2016
• Delving Deeper into Convolutional Networks for Learning Video Representations [Paper] [Review]
  • Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville, ICLR, 2016
• Dynamic Capacity Networks [Paper] [Review]
  • Amjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, Aaron Courville, ICML, 2016
• Identity Mappings in Deep Residual Networks [Paper] [Review]
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, ArXiv, 2016
• Net2Net: Accelerating Learning via Knowledge Transfer [Paper] [Review]
  • Tianqi Chen, Ian Goodfellow, Jonathon Shlens, ICLR, 2016
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution [Paper] [Review]
  • Justin Johnson, Alexandre Alahi, Li Fei-Fei, ArXiv, 2016
• Recurrent Batch Normalization [Paper] [Review]
  • Tim Cooijmans, Nicolas Ballas, César Laurent, Aaron Courville, ArXiv, 2016
• Residual Networks are Exponential Ensembles of Relatively Shallow Networks [Paper] [Review]
  • Andreas Veit, Michael Wilber, Serge Belongie, ArXiv, 2016
• Residual Networks of Residual Networks: Multilevel Residual Networks, ArXiv, 2016 [Paper] [Review]
  • Ke Zhang, Miao Sun, Tony X. Han, Xingfang Yuan, Liru Guo, Tao Liu, ArXiv, 2016

2015

• Deep Visual Analogy-Making [Paper] [Review]
  • Scott E. Reed, Yi Zhang, Yuting Zhang, Honglak Lee, NIPS, 2015
• DenseCap: Fully Convolutional Localization Networks for Dense Captioning [Paper] [Review]
  • Justin Johnson, Andrej Karpathy, Li Fei-Fei, ArXiv, 2015
• DRAW: A Recurrent Neural Network For Image Generation [Paper] [Review]
  • Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra, ICML, 2015
• Neural Machine Translation by Jointly Learning to Align and Translate [Paper] [Review]
  • Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio, ICLR, 2015
• Object Detectors Emerge in Deep Scene CNNs [Paper] [Review]
  • Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba, ICLR, 2015
• Spatial Transformer Networks [Paper] [Review]
  • Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu, NIPS, 2015
• Stacked Attention Networks for Image Question Answering [Paper] [Review]
  • Zichao Yang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Smola, ArXiv, 2015
• Striving for Simplicity: the All Convolutional Net [Paper] [Review]
  • Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, Martin Riedmiller, ICLR, 2015
• You Only Look Once: Unified, Real-Time Object Detection [Paper] [Review]
  • Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, ArXiv15

2014

• Convolutional Neural Networks for Sentence Classification [Paper] [Review]
  • Yoon Kim, EMNLP, 2014
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps [Paper] [Review]
  • Karen Simonyan, Andrea Vedaldi, Andrew Zisserman, ICLR, 2014
• Going Deeper with Convolutions [Paper] [Review]
  • Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, ArXiv, 2014
• How transferable are features in deep neural networks? [Paper] [Review]
  • Jason Yosinski, Jeff Clune, Yoshua Bengio, Hod Lipson, NIPS, 2014
• Intriguing Properties of Neural Netwo