kumarkrishna/paper-spray

List of interesting papers to read

Paper-Spray

This is a list of interesting research papers started by Kumar and Biswa (currently being maintained only by Kumar), mainly in Machine Learning, but definitely not limited to it. This is mainly an initiative to inculcate a reading habit among ourselves. Suggested reads are always welcome!

We would try submit only links which are freely available, but we may also add few links which can be accessed freely only from an university network.

We have created a webpage for Paper-Spray containing a searchable list of the papers in the json file.

Entry format:

• Paper Title Date Added, Keywords Author, Conference, Year

Abbreviations:

• AI: Artificial Intelligence
• CV : Computer Vision
• DL: Deep Learning
• ML : Machine Learning
• NLP : Natural Language Processing
• RL : Reinforcement Learning

How it works?

The papers are added to paper-list.json. They can either be added manually or by using the add_papers.py script. Thereafter the README is generated by using the create_readme.py script. This script appends the paper names present in the json file to the contents of readme.template, to generate README.md.

Some scripts such as add_papers.sh and add_papers_minimal.sh have been created for convenience.

The scripts give a warning when adding duplicate papers. In that case, enter 'n' when asked to abort adding the paper.

The webpage for paper-spray reads the json file and creates a table using js libraries. There is no need of generating static html pages for any change in the json file.

Papers

• Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
  17/08/2017, RL, K-FAC
Yuhuai Wu, Elman Mansimov, Shun Liao, Roger Grosse, Jimmy Ba, arXiv [Review]
• Function Optimization Using Connectionist Reinforcement Learning Algorithms
  16/08/2017, RL
Ronald J. Williams, Jing Peng, Connection Science
• How to Escape Saddle Points Efficiently
  16/08/2017, ML, Non-Convex
Chi Jin, Rong Ge, Praneeth Netrapalli, Sham M. Kakade, Michael I. Jordan, ICML 2017 [Review]
• Emergence of Locomotion Behaviours in Rich Environments
  16/07/2017, RL, Robotics, PPO
Nicolas Heess, Dhruva TB, Srinivasan Sriram, Jay Lemmon, Josh Merel, Greg Wayne, Yuval Tassa, Tom Erez, Ziyu Wang, S. M. Ali Eslami, Martin Riedmiller, David Silver, arXiv
• Continuous control with deep reinforcement learning
  16/07/2017, RL, DDPG
Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra, ICLR 2016
• Trust Region Policy Optimization
  16/07/2017, RL, Robotics
John Schulman, Sergey Levine, Philipp Moritz, Michael Jorda, Pieter Abbeel, ICML, 2015
• The Reversible Residual Network: Backpropagation Without Storing Activations
  14/06/2017, CV, RevNets
Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse, arXiv
• Preconditioning Kernel Matrices
  15/12/2016, kernel methods
Kurt Cutajar, Michael Osborne, John Cunningham, Maurizio Filippone, ICML 2016
• Image-to-Image Translation with Conditional Adversarial Networks
  15/12/2016, CV, DL, GAN
Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A.Efros, arxiv
• Continous Control with Deep Reinforcement Learning
  15/12/2016, DL, RL, DDPG
Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra, ICLR 2016
• Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
  04/12/2016, generative model, latent space
Anh Nguyen, Jason Yosinski, Yoshua Bengio, Alexey Dosovitskiy, Jeff Clune, arXiv
• Semantic Facial Expression Editing using Autoencoded Flow
  04/12/2016, autoencoder, latent space, image manipulation
Raymond Yeh, Ziwei Liu, Dan B Goldman, Aseem Agarwala, arXiv
• Full-Capacity Unitary Recurrent Neural Networks
  02/11/2016, DL
Scott Wisdom, Thomas Powers, John R. Hershey, Jonathan Le Roux, Les Atlas, NIPS 2016
• Conditional Image Synthesis With Auxiliary Classifier GANs
  02/11/2016, CV, DL, GAN
Augustus Odena, Christopher Olan, Jonatho Shlens, arxiv
• Stochastic Variational Deep Kernel Learning
  02/11/2016, DL, ML
Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, Eric P. Xing, NIPS 2016
• Multi-Scale Context Aggregation by Dilated Convolutions
  01/11/2016, CV, DL
Fisher Yu, Vladlen Klotun, ICLR 2016
• Neural Machine Translation in Linear Time
  01/11/2016, NMT, DL, dilated-convolutions
Nal Kalchbrenner, Lasse Espeholt, Karen Simonyan, Aaron van den Oord, Alex Graves, Koray Kavukcuoglu, arxiv
• Recurrent Highway Networks
  01/11/2016, DL, RNN
Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutnik, Jurgen Schmidhuber, arxiv
• Recurrent Switching Linear Dynamical Systems
  31/10/2016, ML
Scott Linderman, Andrew Miller, Ryan Adams, David Blei, Liam Paninski, Matthew Johnson, arxiv
• Operator Variational Inference
  31/10/2016, ML, variational
Rajesh Ranganath, Jaan ALtosaar, Dustin Tran, David M. Blei, arxiv
• Professor Forcing: A New Algorithm for Training Recurrent Networks
  31/10/2016, DL, RNN
Alex Lamb, Anirudh Goyal, Ying Zhang, Saizheng Zhang, Aaron Courville, Yoshua Bengio, NIPS 2016
• Pointer Sentinel Mixture Models
  30/10/2016, DL, NLP
Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher, rxiv
• Can Active Memory Replace Attention?
  28/10/2016, DL
Lukasz Kaiser, Samy Bengio, NIPS 2016
• Analysis of Thompson Sampling for the Multi-armed Bandit Problem
  25/10/2016, Sampling, Bandits
Shipra Agrawal, Navin Goyal, JMLR 2012
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
  25/10/2016, DL, RL
Bradly Stadie, Sergey Levine, Pieter Abbeel, arxiv
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
  22/10/2016, DL, optimization, bayesian
José Miguel Hernández-Lobato, Ryan P. Adams, JMLR
• Towards Deep Symbolic Reinforcement Learning
  21/10/2016, DL, RL
Marta Garnelo, Kai Arulkumaran, Murray Shanahan, arxiv
• Layer Normalization
  21/10/2016, DL, optimization
Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton, arXiv
• A Theory of Generative ConvNet
  21/10/2016, ML, statistics, generative, cnn
Jianwen Xie, Yang Lu, Song-Chun Zhu, Ying Nian Wu, ICML 2016
• Modular Multitask Reinforcement Learning with Policy Sketches
  06/10/2016, RL, policy sketch
Jacob Andreas, Dan Klein, Sergey Levine, ICML 2017
• A Tutorial on Energy-Based Learning
  27/09/2016, ML, energy models
Yann LeCun, Sumit Chopra, Raia Hadsell, Marc’Aurelio Ranzato, and Fu Jie Huang,
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
  21/09/2016, GAN, sequence generation, policy gradient
Lantao Yu, Weinan Zhang, Jun Wang, Yong Yu, arXiv
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  16/09/2016, CV, GAN, super resolution
Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, Wenzhe Shi, arXiv
• Energy-based Generative Adversarial Network
  16/09/2016, GAN, DL, generative model, energy function
Junbo Zhao, Michael Mathieu, Yann LeCun, arXiv
• Generating Videos with Scene Dynamics
  15/09/2016, CV, DL, GAN
Carl Vondrick, Hamed Pirsiavash, Antonio Torralba, NIPS 2016
• Generative Visual Manipulation on the Natural Image Manifold
  15/09/2016, CV, DL, GAN
Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman and Alexei A. Efros, ECCV 2016
• Why does deep and cheap learning work so well?
  10/09/2016, DL, ML, physics
Henry W. Lin, Max Tegmark, arXiv
• Reward Augmented Maximum Likelihood for Neural Structured Prediction
  01/09/2016, DL, RL, MLE
Mohammad Norouzi, Samy Bengio, Zhifeng Chen, Navdeep Jaitly, Mike Schuster, Yonghui Wu, Dale Schuurmans, NIPS 2016
• Densely Connected Convolutional Networks
  28/08/2016, DL, CNN
Gao Huang, Zhuang Liu, Kilian Q. Weinberger, arXiv
• Mollifying Networks
  18/08/2016, ML, optimization
Caglar Gulcehre, Marcin Moczulski, Francesco Visin, Yoshua Bengio, arXiv
• Optimization Methods for Large-Scale Machine Learning
  18/08/2016, ML, optimization
Léon Bottou, Frank E. Curtis, Jorge Nocedal, arXiv
• Deep FisherNet for Object Classification
  02/08/2016, CV, DL, object classification
Peng Tang, Xinggang Wang, Baoguang Shi, Xiang Bai, Wenyu Liu, Zhuowen Tu, arXiv
• Attention-over-Attention Neural Networks for Reading Comprehension
  26/07/2016, DL, NLP, Attention memory
Yiming Cui, Zhipeng Chen, Si Wei, arXiv
• BinaryConnect : Training Deep Neural Networks with binary weights during propagations
  21/07/2016, DL, binary-connect
Matthieu Courbariaux, Yoshua Bengio, Jean-Pierre David, NIPS 2015
• Stochastic backpropagation and approximate inference in deep generative models
  20/07/2016, generative-models
Danilo Jimenez Rezende, Shakir Mohamed, Daan Wierstra, ICML 2014
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
  20/07/2016, MCMC, VAE
Tim Salimans, Diederik P. Kingma, Max Welling, ICML 2015
• Efficient approaches for escaping higher order saddle points in non-convex optimization
  19/07/2016, ML, non-convex-optimization
Anima Anandkumar, Rong Ge, COLT 2016
• Gated-Attention Readers for Text Comprehension
  19/07/2016, DL, NLP
Bhuwan Dhingra, Hanxiao Liu, William W. Cohen, Ruslan Salakhutdinov, arXiv
• Tensor decompositions for learning latent variable models
  19/07/2016, ML, TF
Anima Anandkumar, Rong Ge, Daniel Hsu, Sham M. Kakade, Matus Telgarsky, JMLR 2014
• Pixel Recurrent Neural Networks
  19/07/2016, DL, RNN
Aaron van den Oord, Nal Kalchbrenner, Koray Kavukcuoglu, ICML 2016
• NICE: Non-linear Independent Components Estimation
  18/07/2016, DL
Laurent Dinh, David Krueger, Yoshua Bengio, ICLR 2015
• Higher Order Statistical Decorrelation without Information Loss
  18/07/2016, DL, IT
Gustavo Deco, Wilfried Brauer, NIPS 1995
• Conditional Generative Aversarial Nets
  14/07/2016, GAN, DL
Mehdi Mirza, Simon Osindero, NIPS DL Workshop, 2014
• Neural Generative Question Answering
  14/07/2016, DL, NLP, QA
Jun Yin, Xin Jiang, Zhengdong Lu, Lifeng Shang, Hang Li, Xiaoming Li, ICLR 2016
• A Decomposable Attention Model for Natural Language Inference
  09/07/2016, DL, NLP
Ankur P. Parikh, Oscar Tackstrom, Dipanjan Das, Jakob Uszkoreit, arXiv
• Sequence Level Training with Recurrent Neural Networks
  06/07/2016, DL, RNN
Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, Wojciech Zaremba, ICLR 2016
• Memorability of Image Regions
  04/07/2016, CV, DL
Aditya Khosla, Jianxiong Xiao, Antonio Torralba, Aude Oliva, NIPS 2012
• Character-Aware Neural Language Models
  04/07/2016, DL, NLP
Yoon Kim, Yacine Jernite, David Sontag, Alexander M. Rush, AAAI 2016
• Learning Language Games through Interaction
  03/07/2016, DL, NLP
Sida Wang, Percy Liang, Chris Manning, ACL 2016
• Object Detectors emerge in Deep Scene CNNs
  02/07/2016, CV, DL
Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba, ICLR 2015
• An Infinite Restricted Boltzmann Machine
  01/07/2016, ML, RBM
Marc-Alexandre Cote, Hugo Larochelle, Neural Computation
• Learning to See by Moving
  30/06/2016, CV, DL
Pulkit Agrawal, Joao Carreira, Jitendra Malik, ICCV 2015
• Distinguishing cause from effect using observational data: methods and benchmarks
  29/06/2016, ML, cause-inference
Joris M. Mooij, Jonas Peters, Dominik Janzing, Jakob Zscheischler, Bernhard Scholkopf, JMLR 2016
• Neural Variational Inference for Text Processing
  29/06/2016, DL, NLP
Yishu Miao, Lei Yu, Phil Blunsom, arXiv
• Learning to Transduce with Unbounded Memory
  27/06/2016, DL, NTM, neural data structures
Edward Grefenstette, Karl Moritz Hermann, Mustafa Suleyman, Phil Blunsom, NIPS 2015
• Mean Shift, Mode Seeking, and Clustering
  26/06/2016, ML, Clustering
Yizong Cheng, IEEE, 1995
• Adaptive Online Gradient Descent
  25/06/2016, optimization, gradient descent
Peter L. Bartlett, Elad Hazan, Alexander Rakhlin, NIPS 2007
• Visual Genome
  24/06/2016, vision, nlp multimodal dataset
Ranjay Krishna et. al., Dataset
• Learning Visual Predictive Models of Physics for Playing Billiards
  23/06/2016, CV, DL
Katerina Fragkiadaki, Pulkit Agrawal, Sergey Levine, Jitendra Malik, ICLR 2016
• Tutorial on Variational Autoencoders
  22/06/2016, DL, VAE
Carl Doersch, arXiv
• Towards Conceptual Compression
  22/06/2016, DL
Karol Gregor, Frederic Besse, Danilo Jimenez Rezende, Ivo Danihelka, Daan Wierstra, arXiv
• Dynamic Memory Networks for Visual and Textual Question Answering
  22/06/2016, CV, DL, NLP, MemNets
Caiming Xiong, Stephen Merity, Richard Socher, ICML 2016
• Delving Deeper into Convolutional Networks for Learning Video Representations
  22/06/2016, CV, DL , videos
Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville, ICLR 2016
• Describing Videos by Exploiting Temporal Structure
  22/06/2016, CV, DL, video
Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, Aaron Courville, ICCV 2015
• Generative Adversarial Imitation Learning
  21/06/2016, DL, generative
Jonathan Ho, Stefano Ermon, arXiv
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
  21/06/2016, DL, GAN, f-GAN
Sebastian Nowozin, Botond Cseke, Ryota Tomioka, arXiv
• Variational Inference with Normalizing Flows
  21/06/2016, DL, VAE, inference
Danilo Jimenez Rezende, Shakir Mohamed, ICML 2015
• A Recurrent Latent Variable Model for Sequential Data
  20/06/2016, DL, VRNN
Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron Courville, Yoshua Bengio, NIPS 2015
• Semi-Supervised Learning with Deep Generative Models
  20/06/2016, DL, generative
Diederik P. Kingma, Danilo J. Rezende, Shakir Mohamed, Max Welling, NIPS 2014
• Human-level control through deep reinforcement learning
  19/06/2016, RL, AI, DL
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Nature
• Variational Dropout and the Local Reparameterization Trick
  19/06/2016, DL, dropout
Diederik P. Kingma, Tim Salimans, Max Welling, NIPS 2015
• Ask Your Neurons: A Neural-based Approach to Answering Questions about Images
  19/06/2016, CV, DL, NLP
Mateusz Malinowski, Marcus Rohrbach, Mario Fritz, ICCV 2015
• Generating Images from Captions with Attention
  19/06/2016, CV, DL
Elman Mansimov, Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov, ICLR 2016
• LSTM: A Search Space Odyssey
  19/06/2016, DL, NLP
Klaus Greff, Rupesh Kumar Srivastava, Jan Koutnik, Bas R. Steunebrink, Jurgen Schmidhuber, arXiv
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
  18/06/2016, DL, InfoGAN
Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, Pieter Abbeel, arXiv
• Improved Techniques for Training GANs
  18/06/2016, DL, GAN
Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen, arXiv
• Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units
  17/06/2016, DL, CV
Wenling Shang, Kihyuk Sohn, Diogo Almeida, and Honglak Lee, ICML 2016
• Fast dropout training
  17/06/2016, DL, dropout
Sida I. Wang, Christopher D. Manning, ICML 2013
• Stating the Obvious: Extracting Visual Common Sense Knowledge
  15/06/2016, DL, NLP
Mark Yatskar, Vicente Ordonez, Ali Farhadi, NAACL 2016
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
  15/06/2016, DL, RL
Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, Shimon Whiteson, arXiv
• Safely Interruptible Agents
  15/06/2016, AI, RL, safety
Laurent Orseau, Stuart Armstrong, UAI 2016
• Deep Spatial Autoencoders for Visuomotor Learning
  15/06/2016, CV, DL, RL, robotics
Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeeel, ICRA 2016
• Multi-Bias Non-linear Activation in Deep Neural Networks
  15/06/2016, ML, DL, activation function
Hongyang Li, Wanli Ouyang, Xiaogang Wang, ICML 2016
• Learning Simple Algorithms from Examples
  15/06/2016, ML, DL, AI
Wojciech Zaremba, Tomas Mikolov, Armand Joulin, Rob Fergus, ICML 2016
• Extracting and Composing Robust Features with Denoising Autoencoders
  15/06/2016, DL, DAE
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol, ICML 2008
• Sentence Similarity Learning by Lexical Decomposition and Composition
  14/06/2016, DL, NLP
Zhiguo Wang, Haitao Mi, Abraham Ittycheriah, arXiv
• Learning visual groups from co-occurrences in space and time
  14/06/2016, CV, DL
Phillip Isola, Daniel Zoran, Dilip Krishnan, Edward H. Adelson, ICLR 2016
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
  14/06/2016, CV, DL
William Lotter, Gabriel Kreiman, David Cox, arxiv
• Matching Networks for One Shot Learning
  14/06/2016, DL, one-shot
Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra, arxiv
• Deep Reinforcement Learning in Large Discrete Action Spaces
  14/06/2016, DL, RL
Gabriel Dulac-Arnold, Richard Evans, Hado van Hasselt, Peter Sunehag, Timothy Lillicrap, Jonathan Hunt, Timothy Mann, Theophane Weber, Thomas Degris, Ben Coppin, arxiv
• Composing graphical models with neural networks for structured representations and fast inference
  14/06/2016, DL, graphical-models
Matthew J. Johnson, David Duvenaud, Alexander B. Wiltschko, Sandeep R. Datta, Ryan P. Adams, arXiv
• Skip-Thought Vectors
  13/06/2016, DL, NLP
Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard Zemel, Antonio Torralba, Raquel Urtasun, Sanja Fidler, NIPS 2015
• Visually Indicated Sounds
  12/06/2016, CV, DL
Andrew Owens, Philip Isola, Josh McDermott, Antonio Torralba, Edward Adelson, William Freeman, CVPR 2016
• DRAW: A Recurrent Neural Network for Image Generation
  11/06/2016, CV, DL, DRAW
Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra, JMLR 2015
• Dynamic Capacity Networks
  10/06/2016, DL
Amjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, Aaron Courville, JMLR, 2016
• Denoising Autoencoder with Modulated Lateral Connections learns Invariant Representations of Natural Images
  10/06/2016, CV, DL, ladder-networks
Antii Rasmus, Tapani Raiko, Harri Valpola, ICLR 2015
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
  10/06/2016, CV, DL, DCGAN
Alec Radford, Luke Metz, Soumith Chintala, ICLR 2016
• Improving sentence compression by learning to predict gaze
  09/06/2016, DL, NLP
Sigrid Klerke, Yoav Goldberg, Anders Sogaard, NAACL 2016, Best Short Paper
• Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
  08/06/2016, DL, NLP
Shengxian Wan, Yanyan Lan, Jun Xu, Jiafeng Guo, IJCAI 2016
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
  08/06/2016, DL, CV, GAN, LAPGAN
Emily Denton, Soumith Chintala, Arthur Szlam, Rob Fergus, NIPS 2015
• Neural Module Networks
  08/06/2016, DL, CV, visual QA
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein, arXiv
• A Neural Probabilistic Language Model
  07/06/2016, DL, NLP
Yoshua Bengio, Rejean Ducharme, Pascal Vincent, Christian Jauvin, JMLR 2003
• Adversarially Learned Inference
  07/06/2016, ML, DL, inference, generative model
Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Alex Lamb, Martin Arjovsky, Olivier Mastropietro, Aaron Courville, Subt. NIPS 2016
• Learning to Optimize
  06/06/2016, DL, optimization
Ke Li, Jitendar Malik, arxiv
• Auto-Encoding Variational Bayes
  06/06/2016, VAE
Diederik P Kingma, Max Welling, ICLR 2014
• Language Understanding for Text-based Games Using Deep Reinforcement Learning
  06/06/2016, DL, NLP, RL
Karthik Narasimhan, Tejas Kulkarni, Regina Barzilay, EMNLP 2015
• Retrofitting Word Vectors to Semantic Lexicons
  06/06/2016, NLP, word vectors
Manaal Faruqui, Jesse Dodge, Sujay K. Jauhar, Chris Dyer, Eduard Hovy, Noah A. Smith, NAACL 2015
• Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics
  06/06/2016, ML, non-parametric estimation
Michael U. Gutmann, Aapo Hyvarinen, JMLR 2012
• Training Products of Experts by Minimizing Contrastive Divergence
  06/06/2016, ML, contrastive divergence
Geoffrey E. Hinton, Neural Computation 2002
• Neural Word Embedding as Implicit Matrix Factorization
  06/06/2016, DL, NLP, word vectors
Omer Levy, Yoav Goldberg, NIPS 2014
• Context Encoders: Feature Learning by Inpainting
  05/06/2016, CV, DL, context-encoder
Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, Alexei AEfros, CVPR 2016
• Long Short-term Memory
  04/06/2016, DL, RNN, LSTM
Sepp Hochreiter, Jurgen Schmidhuber, Neural Computation, 1997
• Maxout Networks
  03/06/2016, DL, dropout, maxout
Ian Goodfellow, David Farley, Mehdi Mirza, Aaron Courville, Yoshua Bengio, JMLR 2013
• A Clockwork RNN
  02/06/2016, DL, RNN, clock-work
Jan Koutnik, Klaus Greff, Faustino Gomez, Jurgen Schmidhuber, JMLR 2014
• Long Short-Term Memory-Networks for Machine Reading
  02/06/2016, DL, NLP, machine understanding
Jianpeng Cheng, Li Dong, Mirella Lapata,
• Effective Approaches to Attention-based Neural Machine Translation
  02/06/2016, DL, NLP, neural machine translation
Minh-Thang Luong, Hieu Pham, Christopher D. Manning, EMNLP 2015
• A Neural Attention Model for Sentence Summarization
  02/06/2016, DL, NLP, summarization
Alexander M. Rush, Sumit Chopra, Jason Weston, EMNLP 2015
• To See or not to See : The need for attention to perrceive changes in scenes
  01/06/2016, attention, vision
Ronald Rensink, Kevin O'Regan, James Clark, Psychological Science, 1997
• Teaching Machines to Read and Comprehend
  01/06/2016, DL, NLP, attention
Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom, NIPS 2015
• Recurrent Models of Visual Attention
  01/06/2016, CV, DL, RL, attention
Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu, NIPS 2014
• Learning to compose neural networks for question answering
  01/06/2016, DL, compose-NN, RL, QA
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein, NAACL 2016 (best-paper)
• Asynchronous Methods for Deep Reinforcement Learning
  01/06/2016, DL, RL
Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu, 2016
• Density estimation using Real NVP
  01/06/2016, DL, latent space, image generation
Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio, Google Brain
• Sparse Filtering
  01/06/2016, ML, DL, sparse
Jiquan Ngiam, Pang Wei Koh, Zhenghao Chen, Sonia Bhaskar, Andrew Y. Ng, NIPS 2011
• Reinforcement Learning Neural Turing Machines
  31/05/2016, DL, NTM, RL
Wojciech Zaremba, ICLR 2016
• Neural Networks with Few Multiplications
  31/05/2016, DL, optimization
Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic, Yoshua Bengio, ICLR 2016
• Recurrent neural network based language model
  30/05/2016, DL, NLP, RNN, language-model
Tomas Mikolov, Martin Karafiat, Lukas Burget, Jan Cernocky, Sanjeev Khudanpur, INTERSPEECH 2010
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
  30/05/2016, DL, DMN, NLP, dynamic-memory-networks
Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher, ICML 2016
• Actor-Mimic : Deep Multitask and Transfer Reinforcement Learning
  30/05/2016, DL, RL, actor-mimic
Emilio Parisotto, Jimmy Ba, Ruslan Salakhutdinov, ICLR 2016
• Neural Programmer-Interpreters
  29/05/2016, DL, NPI
Scott Reed, Nando de Freitas, ICLR 2016
• End-to-End Training of Deep Visuomotor Policies
  29/05/2016, CV, DL, RL, robotics, control
Sergey Levine, Chelsea Finn, Trevor Darrell, Pieter Abbeel, JMLR 2016
• MovieQA : Understanding Stories in Movies through Question-Answering
  28/05/2016, CV, DL, QA, movie-story
Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Antonio Torralba, Raquel Urtasun, Sanja Fidler, CVPR 2016
• Order-Embeddings of Images and Language
  28/05/2016, CV, DL, image-caption, hierarchy
Ivan Vendrov, Ryan Kiros, Sanja Fidler, Raquel Urtasun, ICLR 2016
• Action Recognition using Visual Attention
  28/05/2016, CV, DL, action-recognition, attention
Shikhar Sharma, Ryan Kiros, Ruslan Salakhutdinov, ICLR 2016
• End-To-End Memory Networks
  28/05/2016, DL, memory-networks, end-to-end
Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus, NIPS 2015
• Dueling Network Architectures for Deep Reinforcement Learning
  27/05/2016, DL, dueling-networks, RL
Ziyu Whang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot, Nando de Freitas, ICML 2016
• Memory Networks
  27/05/2016, DL, memory-networks
Jason Weston, Sumit Chopra, Antoine Bordes, ICLR 2015
• Playing Atari with Deep Reinforcement Learning
  27/05/2016, DL, DQN, RL
Volodymyr Mnih et al, NIPS DL workshop 2013
• Deep Networks with Stochastic Depth
  27/05/2016, DL, stochastic-depth
Gao Huang, Yu Sun et al, 2016
• An Introduction to Variational Methods for Graphical Models
  26/05/2016, graphical-models, ML, variational-methods
Michael Jordan et al, Machine Learning 1999
• Deep Visual-Semantic Alignments for Generating Image Descriptions
  26/05/2016, CV, DL, image-captioning, NLP
Andrej Karpathy, Li Fei-Fei, CVPR 2015
• VQA : Visual Question Answering
  26/05/2016, CV, DL, QA
Aishwarya Agarwal et al, ICCV 2015
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
  26/05/2016, DL, RNN, scheduled-sampling
Samy Bengio et al, NIPS 2015
• Batch Normalization : Accelerating Deep Network Training by Reducing Covariate Shift
  26/05/2016, batch-norm, DL
Sergey Ioffe, Christian Szegedy, JMLR 2015
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
  25/05/2016, CV, DL, attention, caption
Kelvin Xu et al, JMLR 2015
• Pointer Networks
  24/05/2016, DL, Pointer-Nets
Oriol Vinyals, Meire Fortunato, Navdeep Jaitly, NIPS 2015
• Order Matters : Sequence to Sequence for sets
  24/05/2016, DL, seq2seq, ordered, sorting
Oriol Vinyals, Samy Bengio, Manjunath Kudlur, ICLR 2016
• Neural Machine Translation by Jointly Learning to Align and Translate
  23/05/2016, DL, NMT
Bahdanau, Cho, Bengio, ICLR 2015
• Visualizing Data using t-SNE
  23/05/2016, ML, Embeddings
Maaten, Hinton,, JMLR 2008
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
  22/05/2016, DL, NLP, RNN-ED
Kyunghyun Cho et al, ACL 2014
• Deep Residual Learning for Image Recognition
  22/05/2016, CV, DL, ResNets
Kaiming He et al, 2015
• Neural Turing Machines
  22/05/2016, DL, NTM
Alex Graves et al, 2014
• Support Vector Machine Learning for Interdependent and Structured Output Spaces
  21/05/2016, ML, StructSVM
Ioannis Tsochantaridis et al, ICML 2004
• Generative Adversarial Networks
  21/05/2016, DL, GAN, generative
Ian Goodfellow et al, NIPS 2014
• Sequence to Sequence learning with neural networks
  21/05/2016, DL, Seq2Seq
Ilya Sutskever, Oriol Vinyals, and Quoc Le, NIPS 2014
• Adam : A Method for Stochastic Optimization
  20/05/2016, ML, Optimization, ADAM
Diederik Kingma, Jimmy Ba, ICLR 2015
• Neural GPUs Learn Algorithms
  20/05/2016, DL
Lukasz Kaiser, Ilya Sutskever, ICLR 2016
• Generating Sequences With Recurrent Neural Networks
  19/05/2016, DL
Alex Graves, 2014
• Generative Adversarial Text to Image Synthesis
  19/05/2016, CV, DL
Scott Reed et al, ICML 2016
• Learning word embeddings efficiently with noise-contrastive estimation
  18/05/2016, DL, NLP
Andriy Mnih et al, NIPS 2013
• Generating Sentences from a Continuous Space
  18/05/2016, DL, NLP
Samuel Bowman et al, 2015
• Reinforcement Learning: A Survey
  18/05/2016, AI, ML, RL
Leslie Kaebling et al, JAIR 1996
• Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
  18/05/2016, AI, ML, REINFORCE
Ronald Williams, Machine Learning 1992
• Training Neural Networks Without Gradients: A Scalable ADMM Approach
  17/05/2016, DL
Gavin Taylor et al, ICML 2016
• k-means++: The Advantages of Careful Seeding
  17/05/2016, Clustering, ML
David Arthur et al, SODA 2007
• Bridging the Gaps Betweeen Residual Learning, Recurrent Neural Networks and Visual Cortex
  13/04/2016, CV, DL, cortex
Quanli Liao, Tomas Poggio, arxiv
• Eye movements in natural behaviour
  01/06/2015, eye-movement, attention
Mary Hayhoe, Dana Ballard, Trends in Cognitive Sciences, 2005
• Optimizing Neural Networks with Kronecker-factored Approximate Curvature
  19/03/2015, K-FAC
James Martens, Roger Grosse, ICML 2015
• Randomized Nonlinear Component Analysis
  13/05/2014, RNCA, ML
David Lopez-Paz, Suvrit Sra, Alex Smola, Zoubin Grahramani, Bernhard Scholkopf, ICML, 2014
• On Information and Sufficiency
  01/03/1951, classics, KL-divergence, information theory
S. Kullback and R. A. Leibler, The Annals of Mathematical Statistics [Review]