├── 2015-11-25.md ├── 2016-10-12.md ├── 2016-10-26.md ├── 2016-11-09.md ├── 2016-11-23.md ├── 2016-12-07.md ├── 2017-01-04.md ├── 2017-01-18.md ├── 2017-02-01.md ├── 2017-02-15.md ├── 2017-03-01.md ├── 2017-03-15.md ├── 2017-03-29.md ├── 2017-04-12.md ├── 2017-04-26.md ├── 2017-05-10.md ├── 2017-05-24.md ├── 2017-06-07.md ├── 2017-06-21.md ├── 2017-07-05.md ├── 2017-07-19.md ├── 2017-08-02.md ├── 2017-08-16.md ├── 2017-08-30.md ├── 2017-09-13.md ├── 2017-09-27.md ├── 2017-10-11.md ├── 2017-10-25.md ├── 2017-11-08.md ├── 2017-11-22.md ├── 2017-12-06.md ├── 2018-01-03.md ├── 2018-01-17.md ├── 2018-01-31.md ├── 2018-02-28.md ├── 2018-03-14.md ├── 2018-03-28.md ├── 2018-04-11.md ├── 2018-04-25.md ├── 2018-05-09.md ├── 2018-05-23.md ├── 2018-06-06.md ├── 2018-06-20.md ├── 2018-07-04.md ├── 2018-07-18.md ├── 2018-08-01.md ├── 2018-08-15.md ├── 2018-08-29.md ├── 2018-09-12.md ├── 2018-09-26.md ├── 2018-10-11.md ├── 2018-11-21.md ├── 2018-12-05.md ├── 2018-12-19.md ├── 2019-01-16.md ├── 2019-01-30.md ├── 2019-02-13.md ├── 2019-02-27.md ├── 2019-04-08.md ├── 2020.md ├── 2021.md ├── 2022-11-01.md ├── 2022-11-15.md ├── 2022-11-29.md ├── 2022-12-13.md ├── 2022_Jan_to_Sep.md ├── 2023-01-10.md ├── 2023-01-24.md ├── 2023-02-07.md ├── 2023-03-07.md ├── 2023-10-05.md ├── Deep Clustering ├── Cheat sheet for Deep Clustering.docx └── Cheat sheet for Deep Clustering.pdf ├── Gaussian Processes ├── Gaussian Processes Presentation.pdf ├── Gaussian Processes Presentation.pptx └── Readme.md ├── Other Reference Materials ├── Deep Neural Networks for Youtube Rec.pdf ├── GDPR_CCPA_Comparison-Guide.pdf ├── neurips22-Slides.pdf └── readme.md ├── README.md ├── archives_2016.md ├── image processing ├── README.md └── colorful image colorization.pdf ├── paper_list_summarizer.py ├── presentation_tips.md ├── rating prediction ├── README.md └── dynamic matrix factorization │ ├── Dynamic matrix factorization with social influence.pdf │ └── background papers │ ├── Dynamic Matrix Factorization- A State Space Approach.pdf │ └── Temporal Matrix Factorization for Tracking Concept Drift in Individual User Preferences.pdf ├── slides_tips.md └── summary.md /2015-11-25.md: -------------------------------------------------------------------------------- 1 | # Reading Group Proposals 2 | 3 | ## Chosen paper 4 | 5 | [Parameter estimation for text analysis](http://www.arbylon.net/publications/text-est.pdf), Gregor Heinrich 6 | 7 | ## Other suggestions 8 | 9 | * [Stan: A probabilistic programming language for Bayesian inference and optimization](http://www.stat.columbia.edu/~gelman/research/published/stan_jebs_2.pdf), Andrew Gelman, Daniel Lee, Jiqiang Guo 10 | * [No free lunch theorems for optimization](https://ti.arc.nasa.gov/m/profile/dhw/papers/78.pdf), David H. Wolpert, William G. Macready 11 | * [Towards a Mathematical Theory of Cortical Micro-circuits](http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1000532), Dileep George, Jeff Hawkins 12 | * [Expectation propagation as a way of life: A framework for Bayesian inference on partitioned data](https://arxiv.org/abs/1412.4869), Aki Vehtari, Andrew Gelman, Tuomas Sivula, Pasi Jylänki, Dustin Tran, Swupnil Sahai, Paul Blomstedt, John P. Cunningham, David Schiminovich, Christian Robert 13 | * [The Model Complexity Myth](https://jakevdp.github.io/blog/2015/07/06/model-complexity-myth/), Jake VanderPlas 14 | -------------------------------------------------------------------------------- /2016-10-12.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Origins of Presidential poll aggregation: A perspective from 2004 to 2012](https://web.math.princeton.edu/~sswang/wang15_IJF_origins-of-poll-aggregation.pdf), Samuel S.-H. Wang [\[code\]](http://election.princeton.edu/for-fellow-geeks/) 4 | 5 | ## Other suggestions 6 | 7 | * [DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning](https://www.repository.cam.ac.uk/bitstream/handle/1810/250525/Lane,%20Georgiev,%20%26%20Qendro%202015%20UbiComp.pdf?sequence=1&isAllowed=y), Nicholas D. Lane, Petko Georgiev, Lorena Qendro 8 | * [Equality of Opportunity in Supervised Learning](https://drive.google.com/file/d/0B-wQVEjH9yuhanpyQjUwQS1JOTQ/view), Moritz Hardt, Eric Price, Nathan Srebro 9 | * [Dynamic Memory Networks for Visual and Textual Question Answering](https://arxiv.org/abs/1603.01417), Caiming Xiong, Stephen Merity, Richard Socher 10 | * [Detecting events and key actors in multi-person videos](https://arxiv.org/abs/1511.02917), Vignesh Ramanathan, Jonathan Huang, Sami Abu-El-Haija, Alexander Gorban, Kevin Murphy, Li Fei-Fei 11 | -------------------------------------------------------------------------------- /2016-10-26.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks](https://arxiv.org/abs/1602.03616), Anh Nguyen, Jason Yosinski, Jeff Clune [\[code\]](https://github.com/Evolving-AI-Lab/mfv) 4 | 5 | ## Other suggestions 6 | 7 | * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://arxiv.org/abs/1502.03167), Sergey Ioffe, Christian Szegedy 8 | * [Stealing Machine Learning Models via Prediction APIs](https://arxiv.org/abs/1609.02943), Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, Thomas Ristenpart 9 | * [Hybrid computing using a neural network with dynamic external memory](http://www.nature.com/articles/nature20101.epdf?author_access_token=ImTXBI8aWbYxYQ51Plys8NRgN0jAjWel9jnR3ZoTv0MggmpDmwljGswxVdeocYSurJ3hxupzWuRNeGvvXnoO8o4jTJcnAyhGuZzXJ1GEaD-Z7E6X_a9R-xqJ9TfJWBqz), Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann, Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield, Phil Blunsom, Koray Kavukcuoglu & Demis Hassabis 10 | * [Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables](https://arxiv.org/abs/1604.08880), Nils Y. Hammerla, Shane Halloran, Thomas Ploetz 11 | -------------------------------------------------------------------------------- /2016-11-09.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](http://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks), Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun [\[code\]](https://github.com/smallcorgi/Faster-RCNN_TF) 4 | 5 | ## Other suggestions 6 | 7 | * [Deep Gaussian Processes](http://www.jmlr.org/proceedings/papers/v31/damianou13a.pdf), Andreas C. Damianou, Neil D. Lawrence 8 | * [Stealing Machine Learning Models via Prediction APIs](https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/tramer), Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, Thomas Ristenpart [\[code\]](https://github.com/ftramer/Steal-ML) 9 | * [Distilling the Knowledge in a Neural Network](https://arxiv.org/abs/1503.02531), Geoffrey Hinton, Oriol Vinyals, Jeff Dean 10 | -------------------------------------------------------------------------------- /2016-11-23.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [The Parable of Google Flu: Traps in Big Data Analysis](http://science.sciencemag.org/content/343/6176/1203), David Lazer, Ryan Kennedy, Gary King, Alessandro Vespignani 4 | 5 | ## Other suggestions 6 | 7 | * [Hybrid computing using a neural network with dynamic external memory](http://www.nature.com/nature/journal/v538/n7626/abs/nature20101.html), Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann, Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield, Phil Blunsom, Koray Kavukcuoglu & Demis Hassabis 8 | * [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385), Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun 9 | * [Playing FPS Games with Deep Reinforcement Learning](https://arxiv.org/abs/1609.05521), Guillaume Lample, Devendra Singh Chaplot 10 | * [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://arxiv.org/abs/1611.04558), Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, Jeffrey Dean 11 | -------------------------------------------------------------------------------- /2016-12-07.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Building Machines That Learn and Think Like People](https://arxiv.org/abs/1604.00289), Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman 4 | 5 | ## Other suggestions 6 | 7 | * [A density-based algorithm for discovering clusters in large spatial databases with noise](https://webdocs.cs.ualberta.ca/~zaiane/courses/cmput695-00/papers/00153.pdf), M Ester, HP Kriegel, J Sander, X Xu 8 | * [Survival Analysis Part I: Basic concepts and first analyses](http://www.slaop.org/pdf/814Journ7.pdf), TG Clark, MJ Bradburn, SB Love and DG Altman 9 | * [Quantifying the evolution of individual scientific impact](http://www.dashunwang.com/pdf/Sinatra2016-Science.pdf), R Sinatra, D Wang, P Deville, C Song, A-L Barabási 10 | -------------------------------------------------------------------------------- /2017-01-04.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Exploring Online Ad Images Using a Deep Convolutional Neural Network Approach](https://arxiv.org/abs/1509.00568), Michael Fire, Jonathan Schler 4 | 5 | ## Other suggestions 6 | 7 | * [In-season prediction of batting averages: A field test of empirical Bayes and Bayes methodologies](https://arxiv.org/abs/0803.3697), Lawrence D. Brown 8 | * [Human-level concept learning through probabilistic program induction](http://web.mit.edu/cocosci/Papers/Science-2015-Lake-1332-8.pdf), Brenden M. Lake, Ruslan Salakhutdinov, Joshua B. Tenenbaum 9 | * [#HashtagWars: Learning a Sense of Humor](https://arxiv.org/abs/1612.03216), Peter Potash, Alexey Romanov, Anna Rumshisky 10 | -------------------------------------------------------------------------------- /2017-01-18.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://arxiv.org/abs/1701.01724), Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Michael Bowling 4 | 5 | ## Other suggestions 6 | 7 | * [Unrolled Generative Adversarial Networks](https://arxiv.org/abs/1611.02163), Luke Metz, Ben Poole, David Pfau, Jascha Sohl-Dickstein 8 | * [Cluster failure: Why fMRI inferences for spatial extent have inflated false-positive rates](http://www.pnas.org/content/113/28/7900.full.pdf), Anders Eklunda, Thomas E. Nicholsd, and Hans Knutssona 9 | * [Beyond Object Recognition: Visual Sentiment Analysis with Deep Coupled Adjective and Noun Neural Networks](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/08/ijcai16.pdf), Jingwen Wang, Jianlong Fu, Yong Xu, Tao Mei 10 | * [Privacy-Preserving Data Analysis for the Federal Statistical Agencies](https://arxiv.org/abs/1701.00752), John Abowd, Lorenzo Alvisi, Cynthia Dwork, Sampath Kannan, Ashwin Machanavajjhala, Jerome Reiter 11 | -------------------------------------------------------------------------------- /2017-02-01.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Deep clustering: Discriminative embeddings for segmentation and separation](https://arxiv.org/abs/1508.04306), John R. Hershey, Zhuo Chen, Jonathan Le Roux, Shinji Watanabe 4 | 5 | ## Other suggestions 6 | 7 | * [A Conceptual Introduction to Hamiltonian Monte Carlo](https://arxiv.org/abs/1701.02434), Michael Betancourt 8 | * [Latent Dirichlet Allocation](http://www.jmlr.org/papers/v3/blei03a.html), David M. Blei, Andrew Y. Ng, Michael I. Jordan 9 | * [On using expert opinion in ecological analyses: a frequentist approach](http://www.stat.ualberta.ca/~slele/publications/LeleAllen06.pdf), Subhash R. Lele, Kristie L. Allen 10 | * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://arxiv.org/abs/1502.03167), Sergey Ioffe, Christian Szegedy 11 | 12 | ## Bonus extra suggestion for LDA 13 | 14 | * [Finding scientific topics](http://www.pnas.org/content/101/suppl_1/5228.short), Thomas L. Griffiths, Mark Steyvers 15 | -------------------------------------------------------------------------------- /2017-02-15.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Understanding deep learning requires rethinking generalization](https://arxiv.org/abs/1611.03530), Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals 4 | 5 | ## Other suggestions 6 | 7 | * [Safe and Nested Endgame Solving for Imperfect-Information Games](https://www.cs.cmu.edu/~noamb/papers/17-AAAI-Refinement.pdf), Noam Brown, Tuomas Sandholm 8 | * [Automatic Differentiation Variational Inference](https://arxiv.org/abs/1603.00788), Alp Kucukelbir, Dustin Tran, Rajesh Ranganath, Andrew Gelman, David M. Blei 9 | * [Negative training data can be harmful to text classification](http://dl.acm.org/citation.cfm?id=1870680), Xiao-Li Li, Bing Liu, See-Kiong Ng 10 | -------------------------------------------------------------------------------- /2017-03-01.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://arxiv.org/abs/1701.08734), Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, Daan Wierstra 4 | 5 | ## Other suggestions 6 | 7 | * [DeepCoder: Learning to Write Programs](https://arxiv.org/abs/1611.01989), Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow 8 | * [Negative training data can be harmful to text classification](http://dl.acm.org/citation.cfm?id=1870680), Xiao-Li Li, Bing Liu, See-Kiong Ng 9 | * [Forecasting at Scale](https://facebookincubator.github.io/prophet/static/prophet_paper_20170113.pdf), Sean J. Taylor and Benjamin Letham \[[blog post](https://research.fb.com/prophet-forecasting-at-scale/)\] 10 | -------------------------------------------------------------------------------- /2017-03-15.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Modeling Customer Lifetimes with Multiple Causes of Churn](http://people.stat.sfu.ca/~dac5/meetup1/churn.pdf), Michael Braun, David A. Schweidel 4 | 5 | ## Other suggestions 6 | 7 | * [Deep Voice: Real-time Neural Text-to-Speech](https://arxiv.org/abs/1702.07825), Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, Yongguo Kang, Xian Li, John Miller, Andrew Ng, Jonathan Raiman, Shubho Sengupta, Mohammad Shoeybi \[[blog post](http://research.baidu.com/deep-voice-production-quality-text-speech-system-constructed-entirely-deep-neural-networks/)\] 8 | * [Asynchronous Methods for Deep Reinforcement Learning](https://arxiv.org/abs/1602.01783), Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu 9 | * [Is most published research really false?](http://biorxiv.org/content/early/2016/04/27/050575), Jeffrey T Leek, Leah R Jager 10 | * [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://arxiv.org/abs/1703.03864), Tim Salimans, Jonathan Ho, Xi Chen, Ilya Sutskever 11 | -------------------------------------------------------------------------------- /2017-03-29.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Genotype–environment interactions in mouse behavior: A way out of the problem](https://www.researchgate.net/profile/Ilan_Golani/publication/7969318_Genotype-environment_interactions_in_mouse_behavior_A_way_out_of_the_problem/links/00b7d51d2cdac02d7f000000.pdf), Neri Kafkafi, Yoav Benjamini, Anat Sakov, Greg I. Elmer, and Ilan Golani 4 | 5 | ## Other suggestions 6 | 7 | * [Universal adversarial perturbations](https://arxiv.org/abs/1610.08401), Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard 8 | * [Deep Voice: Real-time Neural Text-to-Speech](https://arxiv.org/abs/1702.07825), Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, Yongguo Kang, Xian Li, John Miller, Andrew Ng, Jonathan Raiman, Shubho Sengupta, Mohammad Shoeybi \[[blog post](http://research.baidu.com/deep-voice-production-quality-text-speech-system-constructed-entirely-deep-neural-networks/)\] 9 | * [Ambulance Location for Maximum Survival](https://sites.ualberta.ca/~aingolfs/documents/survival15november07.pdf), Erhan Erkut, Armann Ingolfsson, Güneş Erdoğan 10 | * [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://arxiv.org/abs/1603.05279), Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi 11 | -------------------------------------------------------------------------------- /2017-04-12.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Deep Probabilistic Programming](https://arxiv.org/abs/1701.03757), Dustin Tran, Matthew D. Hoffman, Rif A. Saurous, Eugene Brevdo, Kevin Murphy, David M. Blei 4 | 5 | ## Other suggestions 6 | 7 | * [Multi-talker Speech Separation and Tracing with Permutation Invariant Training of Deep Recurrent Neural Networks](https://arxiv.org/abs/1703.06284), Morten Kolbæk, Dong Yu, Zheng-Hua Tan, Jesper Jensen 8 | * [Constraints versus Priors](http://www.stat.berkeley.edu/~stark/Preprints/constraintsPriors14.pdf), Philip B. Stark 9 | * [Forecasting at Scale](https://facebookincubator.github.io/prophet/static/prophet_paper_20170113.pdf), Sean J. Taylor and Benjamin Letham 10 | * [Asymptotically exact inference in differentiable generative models](http://proceedings.mlr.press/v54/graham17a.html), Matthew Graham, Amos Storkey 11 | * [Judgment under Uncertainty: Heuristics and Biases](http://psiexp.ss.uci.edu/research/teaching/Tversky_Kahneman_1974.pdf), Amos Tversky, Daniel Kahneman 12 | -------------------------------------------------------------------------------- /2017-04-26.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | \[paywalled\] [Statistical modelling of a terrorist network](http://onlinelibrary.wiley.com/doi/10.1111/rssa.12233/full), Murray Aitkin, 4 | Duy Vu, Brian Francis \[[slides](http://mathsofplanetearth.org.au/wp-content/uploads/2013/07/Aitkin-Murray.pdf)\] 5 | 6 | ## Other suggestions 7 | 8 | * [Constraints versus priors](http://www.stat.berkeley.edu/~stark/Preprints/constraintsPriors14.pdf), Philip B. Stark 9 | * [To explain or to predict?](https://arxiv.org/abs/1101.0891), Galit Shmueli 10 | * [Collaborative filtering for implicit feedback datasets](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.167.5120&rep=rep1&type=pdf), Yifan Hu, Yehuda Koren, Chris Volinsky 11 | -------------------------------------------------------------------------------- /2017-05-10.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Semi-supervised knowledge transfer for deep learning from private training data](https://arxiv.org/abs/1610.05755), Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal Talwar 4 | 5 | ## Other suggestions 6 | 7 | * [Collaborative filtering for implicit feedback datasets](http://ieeexplore.ieee.org/abstract/document/4781121/), Yifan Hu, Yehuda Koren, Chris Volinsky \[[pdf](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.167.5120&rep=rep1&type=pdf)\] 8 | * [Model-based biclustering of clickstream data](http://www.sciencedirect.com/science/article/pii/S0167947314002771) \[paywalled\], Volodymyr Melnykov 9 | * [Phase-functioned neural networks for character control](http://www.ipab.inf.ed.ac.uk/cgvu/phasefunction.pdf), Daniel Holden, Taku Komura, Jun Saito 10 | * [Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations](http://onlinelibrary.wiley.com/doi/10.1111/j.1467-9868.2008.00700.x/full), Håvard Rue, Sara Martino, Nicolas Chopin \[[pdf](http://people.ee.duke.edu/~lcarin/inla-rss.pdf)\] 11 | -------------------------------------------------------------------------------- /2017-05-24.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Constraints versus priors](https://www.stat.berkeley.edu/~stark/Preprints/constraintsPriors15.pdf), Philip B. Stark 4 | 5 | ## Other suggestions 6 | 7 | * [Modelling illegal drug participation](http://onlinelibrary.wiley.com/doi/10.1111/rssa.12252/full), Sarah Brown, Mark N. Harris, Preety Srivastava, Xiaohui Zhang 8 | * [Learning to learn by gradient descent by gradient descent](http://papers.nips.cc/paper/6461-learning-to-learn-by-gradient-descent-by-gradient-descent), Marcin Andrychowicz, Misha Denil, Sergio Gómez Colmenarejo, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas 9 | * [ML confidential: machine learning on encrypted data](http://cryptosith.org/papers/mlconf-20130212.pdf), Thore Graepel, Kristin Lauter, and Michael Naehrig 10 | * [Using stacking to average Bayesian predictive distributions](https://arxiv.org/abs/1704.02030), Yuling Yao, Aki Vehtari, Daniel Simpson, Andrew Gelman 11 | -------------------------------------------------------------------------------- /2017-06-07.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Pixel Recurrent Neural Networks](https://arxiv.org/abs/1601.06759), Aäron van den Oord, Nal Kalchbrenner, Koray Kavukcuoglu \[[notes](http://singsoftnext.com/pixel-recurrent-neural-networks/)\] 4 | 5 | ## Other suggestions 6 | 7 | * [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993), Gao Huang, Zhuang Liu, Kilian Q. Weinberger, Laurens van der Maaten 8 | * [Large-Scale Evolution of Image Classifiers](https://arxiv.org/abs/1703.01041), Esteban Real, Sherry Moore, Andrew Selle, Saurabh Saxena, Yutaka Leon Suematsu, Jie Tan, Quoc Le, Alex Kurakin 9 | -------------------------------------------------------------------------------- /2017-06-21.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Introduction to Nonnegative Matrix Factorization](https://pdfs.semanticscholar.org/377f/81ef8f46f8f26e565a6a379cac6cae31f68f.pdf), Nicolas Gillis 4 | 5 | ## Other suggestions 6 | 7 | * [Collaborative Filtering for Implicit Feedback Datasets](http://yifanhu.net/PUB/cf.pdf), Yifan Hu, Yehuda Koren, Chris Volinsky 8 | * [Manifold Relevance Determination](https://arxiv.org/abs/1206.4610), Andreas Damianou, Carl Ek, Michalis Titsias, Neil Lawrence 9 | * [DART: Dropouts meet Multiple Additive Regression Trees](http://proceedings.mlr.press/v38/korlakaivinayak15.pdf), K. V. Rashmi, Ran Gilad-Bachrach 10 | * [Count-ception: Counting by Fully Convolutional Redundant Counting](https://arxiv.org/abs/1703.08710), Joseph Paul Cohen, Henry Z. Lo, Yoshua Bengio 11 | -------------------------------------------------------------------------------- /2017-07-05.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://arxiv.org/abs/1703.04977), Alex Kendall, Yarin Gal 4 | 5 | ## Other suggestions 6 | 7 | * [Surprise Search: Beyond Objectives and Novelty](http://antoniosliapis.com/papers/surprise_search_beyond_objectives_and_novelty.pdf), Daniele Gravina, Antonios Liapis, Georgios N. Yannakakis 8 | * [Two Decades of Recommender Systems at Amazon.com](http://ieeexplore.ieee.org/abstract/document/7927889/), Brent Smith, Greg Linden 9 | * [Data Programming: Creating Large Training Sets, Quickly](http://papers.nips.cc/paper/6523-data-programming-creating-large-training-sets-quickly), Alexander J. Ratner, Christopher M. De Sa, Sen Wu, Daniel Selsam, Christopher Ré 10 | -------------------------------------------------------------------------------- /2017-07-19.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Tutorial on Variational Autoencoders](https://arxiv.org/abs/1606.05908), Carl Doersch 4 | 5 | ## Other suggestions 6 | 7 | * [Data Programming: Creating Large Training Sets, Quickly](https://arxiv.org/abs/1605.07723), Alexander Ratner, Christopher De Sa, Sen Wu, Daniel Selsam, Christopher Ré 8 | * [Climbing the Kaggle Leaderboard by Exploiting the Log-Loss Oracle](https://arxiv.org/abs/1707.01825), Jacob Whitehill 9 | -------------------------------------------------------------------------------- /2017-08-02.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://arxiv.org/abs/1706.05125), Lewis, Yarats, Dauphin, Parikh, Batra \[[blog](https://code.facebook.com/posts/1686672014972296/deal-or-no-deal-training-ai-bots-to-negotiate/)\] \[[code](https://github.com/facebookresearch/end-to-end-negotiator)\] 4 | 5 | ## Other suggestions 6 | 7 | * [Data Programming: Creating Large Training Sets, Quickly](https://arxiv.org/abs/1605.07723), Ratner, De Sa, Wu, Selsam, Ré 8 | * [BIRDNEST: Bayesian Inference for Ratings-Fraud Detection](https://arxiv.org/abs/1511.06030), Hooi, Shah, Beutel, Gunnemann, Akoglu, Kumar, Makhija, Faloutsos 9 | * [Stealing Machine Learning Models via Prediction APIs](https://www.usenix.org/system/files/conference/usenixsecurity16/sec16_paper_tramer.pdf), Tramèr, Zhang, Juels, Reiter, Ristenpart \[[slides](https://www.usenix.org/sites/default/files/conference/protected-files/security16_slides_tramer.pdf)\] \[[code](https://github.com/ftramer/Steal-ML)\] [\[video](https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/tramer)\] 10 | -------------------------------------------------------------------------------- /2017-08-16.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Variational Inference: A Review for Statisticians](https://arxiv.org/abs/1601.00670), David M. Blei, Alp Kucukelbir, Jon D. McAuliffe 4 | 5 | ## Other suggestions 6 | 7 | * [Challenges in Data-to-Document Generation](https://arxiv.org/abs/1707.08052), Sam Wiseman, Stuart M. Shieber, Alexander M. Rush 8 | * [Transitive Invariance for Self-supervised Visual Representation Learning](https://arxiv.org/abs/1708.02901), Xiaolong Wang, Kaiming He, Abhinav Gupta 9 | * [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747), Sebastian Ruder 10 | * [Engineering Efficient and Effective Non-Metric Space Library](https://www.researchgate.net/profile/Leonid_Boytsov/publication/275023439_Engineering_Efficient_and_Effective_Non-metric_Space_Library/links/552ec83d0cf2acd38cbbd828.pdf), Leonid Boytsov and Bilegsaikhan Naidan 11 | -------------------------------------------------------------------------------- /2017-08-30.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [A Brief Survey of Deep Reinforcement Learning](https://arxiv.org/abs/1708.05866), Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath 4 | 5 | ## Other suggestions 6 | 7 | * [Methodologies for Cross-Domain Data Fusion: An Overview](http://ieeexplore.ieee.org/abstract/document/7230259/), Yu Zheng \[[pdf](https://pdfs.semanticscholar.org/fe9d/375dd02a8504b7c5c011e3696e6e6f63f537.pdf)\] 8 | * [Transitive Invariance for Self-supervised Visual Representation Learning](https://arxiv.org/abs/1708.02901), Xiaolong Wang, Kaiming He, Abhinav Gupta 9 | * [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747), Sebastian Ruder 10 | * [Engineering Efficient and Effective Non-Metric Space Library](https://www.researchgate.net/profile/Leonid_Boytsov/publication/275023439_Engineering_Efficient_and_Effective_Non-metric_Space_Library/links/552ec83d0cf2acd38cbbd828.pdf), Leonid Boytsov and Bilegsaikhan Naidan 11 | -------------------------------------------------------------------------------- /2017-09-13.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Learning to learn by gradient descent by gradient descent](http://papers.nips.cc/paper/6461-learning-to-learn-by-gradient-descent-by-gradient-descent.pdf), Marcin Andrychowicz, Misha Denil, Sergio Gómez Colmenarejo, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas 4 | 5 | ## Other suggestions 6 | 7 | * [Evidence of bias in the Eurovision song contest: modelling the votes using Bayesian hierarchical models](http://www.tandfonline.com/doi/full/10.1080/02664763.2014.909792), Marta Blangiardo, Gianluca Baio 8 | * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://arxiv.org/abs/1502.03167), Sergey Ioffe, Christian Szegedy 9 | * [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://arxiv.org/abs/1708.06733), Tianyu Gu, Brendan Dolan-Gavitt, Siddharth Garg 10 | * [Attentive Recurrent Comparators](https://arxiv.org/abs/1703.00767), Pranav Shyam, Shubham Gupta, Ambedkar Dukkipati 11 | -------------------------------------------------------------------------------- /2017-09-27.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Evidence of bias in the Eurovision song contest: modelling the votes using Bayesian hierarchical models](https://arxiv.org/abs/1308.6312), Marta Blangiardo, Gianluca Baio 4 | 5 | ## Other suggestions 6 | 7 | * [Data Programming: Creating Large Training Sets, Quickly](https://arxiv.org/abs/1605.07723), Ratner, De Sa, Wu, Selsam, Ré 8 | * [“Why Should I Trust You?” Explaining the Predictions of Any Classifier](https://arxiv.org/pdf/1602.04938v1.pdf), Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin 9 | * [Opening the Black Box of Deep Neural Networks via Information](https://arxiv.org/abs/1703.00810), Ravid Shwartz-Ziv, Naftali Tishby 10 | -------------------------------------------------------------------------------- /2017-10-11.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [If correlation doesn’t imply causation, then what does?](http://www.michaelnielsen.org/ddi/if-correlation-doesnt-imply-causation-then-what-does/), Michael Nielsen 4 | 5 | ## Other suggestions 6 | 7 | * [Multi-Scale Context Aggregation by Dilated Convolutions](https://arxiv.org/abs/1511.07122), Fisher Yu, Vladlen Koltun 8 | * [Perturbations in Epidemiological Models: When zombies attack, we can survive!](http://www.tandfonline.com/doi/pdf/10.1080/23737867.2014.11414478), Robert F. Allen, Cassandra Jens & Theodore J. Wendt 9 | -------------------------------------------------------------------------------- /2017-10-25.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Speech Enhancement Using Bayesian Wavenet](https://pdfs.semanticscholar.org/1031/1242b016349ba14b56b5554353cf820985c9.pdf), Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Dinei Florencio, Mark Hasegawa-Johnson \[[code](https://github.com/auspicious3000/WaveNet-Enhancement)\] 4 | 5 | ## Other suggestions 6 | 7 | * [Age Progression/Regression by Conditional Adversarial Autoencoder](https://arxiv.org/abs/1702.08423), Zhifei Zhang, Yang Song, Hairong Qi 8 | * [Trust in numbers](http://www.rss.org.uk/Images/PDF/events/2017/President's-address-June-2017.pdf), David Spiegelhalter 9 | * [Training recurrent networks online without backtracking](https://arxiv.org/abs/1507.07680), Yann Ollivier, Corentin Tallec, Guillaume Charpiat 10 | * [Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion](https://www.cs.cmu.edu/~nlao/publication/2014.kdd.pdf), Xin Luna Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, Wei Zhang 11 | * [Perturbations in Epidemiological Models: When zombies attack, we can survive!](http://www.tandfonline.com/doi/pdf/10.1080/23737867.2014.11414478), Robert F. Allen, Cassandra Jens & Theodore J. Wendt 12 | -------------------------------------------------------------------------------- /2017-11-08.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Dynamic Routing Between Capsules](http://papers.nips.cc/paper/6975-dynamic-routing-between-capsules), Sara Sabour, Nicholas Frosst, Geoffrey E. Hinton 4 | 5 | ## Other suggestions 6 | 7 | * [Word Translation Without Parallel Data](https://arxiv.org/abs/1710.04087), Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou 8 | * [Practical Bayesian Inference for Record Linkage](https://arxiv.org/abs/1710.10558), Brendan S. McVeigh, Jared S. Murray 9 | * [Deep Illumination: Approximating Dynamic Global Illumination with Generative Adversarial Network](https://arxiv.org/abs/1710.09834), Manu Mathew Thomas, Angus G. Forbes 10 | * [WaveNet: A Generative Model for Raw Audio](https://arxiv.org/abs/1609.03499), Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, Koray Kavukcuoglu 11 | * [Conditional Random Fields as Recurrent Neural Networks](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zheng_Conditional_Random_Fields_ICCV_2015_paper.pdf), Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet, Zhizhong Su3 Dalong Du, Chang Huang, Philip H. S. Torr 12 | -------------------------------------------------------------------------------- /2017-11-22.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Solving a Higgs optimization problem with quantum annealing for machine learning](https://www.nature.com/articles/nature24047), Alex Mott, Joshua Job, Jean-Roch Vlimant, Daniel Lidar & Maria Spiropulu 4 | 5 | ## Other suggestions 6 | 7 | * [Bayesian Inference for Assessing Effects of Email Marketing Campaigns](https://dash.harvard.edu/bitstream/handle/1/28552972/Wu_Li_Liu2016.pdf?sequence=4), Wu, Jiexing, Kate J. Li, and Jun S. Liu 8 | * [Why Neurons Have Thousands of Synapses, a Theory of Sequence Memory in Neocortex](https://www.frontiersin.org/articles/10.3389/fncir.2016.00023/full), Jeff Hawkins and Subutai Ahmad 9 | * [Matrix capsules with EM routing](https://openreview.net/forum?id=HJWLfGWRb), Geoffrey E Hinton, Sara Sabour, Nicholas Frosst 10 | * [End-To-End Memory Networks](http://papers.nips.cc/paper/5846-end-to-end-memory-networks), Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus 11 | -------------------------------------------------------------------------------- /2017-12-06.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Opening the Black Box of Deep Neural Networks via Information](https://arxiv.org/abs/1703.00810), Ravid Shwartz-Ziv, Naftali Tishby 4 | 5 | ## Other suggestions 6 | 7 | * [Understanding deep learning requires rethinking generalization](https://arxiv.org/abs/1611.03530), Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals 8 | * [Transformation invariant and outlier revealing dimensionality reduction using triplet embedding](https://pdfs.semanticscholar.org/4f45/7460407241fc4872dd7bfaad7771e6a4b081.pdf), Ehsan Amid, Manfred K. Warmuth 9 | * [When to conduct probabilistic linkage vs. deterministic linkage? A simulation study](https://www.sciencedirect.com/science/article/pii/S1532046415000921), Y Zhu, Y Matsuyama, Y Ohashi, S Setoguchi 10 | * [Word Translation Without Parallel Data](https://arxiv.org/abs/1710.04087), Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou 11 | * [Learning Transferable Architectures for Scalable Image Recognition](https://arxiv.org/abs/1707.07012), Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le 12 | -------------------------------------------------------------------------------- /2018-01-03.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [PD-Sparse : A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification](http://proceedings.mlr.press/v48/yenb16.pdf), Ian E. H. Yen, Xiangru Huang, Kai Zhong, Pradeep Ravikumar, Inderjit S. Dhillon 4 | 5 | ## Other suggestions 6 | 7 | * [DeepZip: Lossless Compression using Recurrent Networks](https://pdfs.semanticscholar.org/6a70/3b8be6db81af05628ff6897feb6bf8940a8d.pdf), Kedar Tatwawadi 8 | * [Equation-free mechanistic ecosystem forecasting using empirical dynamic modeling](http://www.pnas.org/content/112/13/E1569.long), Hao Ye, Richard J. Beamish, Sarah M. Glaser, Sue C. H. Grant, Chih-hao Hsieh, Laura J. Richards, Jon T. Schnute and George Sugihara 9 | * [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://arxiv.org/abs/1712.01815), David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis 10 | -------------------------------------------------------------------------------- /2018-01-17.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Probabilistic record linkage](https://academic.oup.com/ije/article-lookup/doi/10.1093/ije/dyv322), Adrian Sayers, Yoav Ben-Shlomo, Ashley W Blom and Fiona Steele 4 | 5 | ## Other suggestions 6 | 7 | * [You Only Look Once: Unified, Real-Time Object Detection](https://arxiv.org/abs/1506.02640), Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi 8 | * [Virtual Adversarial Ladder Networks For Semi-supervised Learning](https://arxiv.org/abs/1711.07476), Saki Shinoda, Daniel E. Worrall, Gabriel J. Brostow 9 | * [Equation-free mechanistic ecosystem forecasting using empirical dynamic modeling](http://www.pnas.org/content/112/13/E1569.long), Hao Ye, Richard J. Beamish, Sarah M. Glaser, Sue C. H. Grant, Chih-hao Hsieh, Laura J. Richards, Jon T. Schnute and George Sugihara 10 | * [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://arxiv.org/abs/1712.01815), David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis 11 | * [Character-level Convolutional Networks for Text Classification](http://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classifica), Xiang Zhang, Junbo Zhao, Yann LeCun 12 | -------------------------------------------------------------------------------- /2018-01-31.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Missing-data imputation](http://www.stat.columbia.edu/~gelman/arm/missing.pdf), Andrew Gelman and Jennifer Hill 4 | 5 | ## Other suggestions 6 | 7 | * [Hybrid computing using a neural network with dynamic external memory](https://ora.ox.ac.uk/objects/uuid:dd8473bd-2d70-424d-881b-86d9c9c66b51/datastreams/bine2aea0d2-0f9c-43a5-b551-c9570284d9f0), A Graves, G Wayne, M Reynolds, T Harley, I Danihelka 8 | * [Spherical CNNS](https://openreview.net/pdf?id=Hkbd5xZRb), Taco S. Cohen, Mario Geiger, Jonas Köhler, Max Welling 9 | * [You Only Look Once: Unified, Real-Time Object Detection](https://arxiv.org/abs/1506.02640), Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi 10 | -------------------------------------------------------------------------------- /2018-02-28.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Distilling the Knowledge in a Neural Network](https://arxiv.org/abs/1503.02531), Geoffrey Hinton, Oriol Vinyals, Jeff Dean 4 | 5 | ## Other suggestions 6 | 7 | * [Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings](https://arxiv.org/abs/1712.06961), Hanan Aldarmaki, Mahesh Mohan, Mona Diab 8 | * [The philosophy of Bayes factors and the quantification of statistical evidence](https://www.sciencedirect.com/science/article/pii/S0022249615000723), Richard D. Morey, Jan-Willem Romeijn, Jeffrey N. Rouder 9 | * [The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets](https://arxiv.org/abs/1802.08232), Nicholas Carlini, Chang Liu, Jernej Kos, Úlfar Erlingsson, Dawn Song 10 | -------------------------------------------------------------------------------- /2018-03-14.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Deep Image Prior](https://arxiv.org/abs/1711.10925), Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky \[[blog](https://dmitryulyanov.github.io/deep_image_prior)\] \[[supplementary material](https://box.skoltech.ru/index.php/s/ib52BOoV58ztuPM#pdfviewer)\] \[[code](https://github.com/DmitryUlyanov/deep-image-prior)\] 4 | 5 | ## Other suggestions 6 | 7 | * [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://arxiv.org/abs/1803.03453), Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Julie Beaulieu, Peter J. Bentley, Samuel Bernard, Guillaume Belson, David M. Bryson, Nick Cheney, Antoine Cully, Stephane Donciuex, Fred C. Dyer, Kai Olav Ellefsen, Robert Feldt, Stephan Fischer, Stephanie Forrest, Antoine Frénoy, Christian Gagneé, Leni Le Goff, Laura M. Grabowski, Babak Hodjat, Laurent Keller, Carole Knibbe, Peter Krcah, Richard E. Lenski, Hod Lipson, Robert MacCurdy, Carlos Maestre, Risto Miikkulainen, Sara Mitri, David E. Moriarty, Jean-Baptiste Mouret, Anh Nguyen, Charles Ofria, Marc Parizeau, David Parsons, Robert T. Pennock, William F. Punch, Thomas S. Ray, Marc Schoenauer, Eric Shulte, Karl Sims, Kenneth O. Stanley, François Taddei, Danesh Tarapore, Simon Thibault, Westley Weimer, Richard Watson, et al. (1 additional author not shown) 8 | * [Distilling a Neural Network Into a Soft Decision Tree](https://arxiv.org/abs/1711.09784), Nicholas Frosst, Geoffrey Hinton 9 | -------------------------------------------------------------------------------- /2018-03-28.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Self-Normalizing Neural Networks](https://arxiv.org/abs/1706.02515), Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter 4 | 5 | ## Other suggestions 6 | 7 | * [Improving Generalization Performance by Switching from Adam to SGD](https://arxiv.org/abs/1712.07628), Nitish Shirish Keskar, Richard Socher 8 | * [Can you Trust the Trend: Discovering Simpson's Paradoxes in Social Data](https://arxiv.org/abs/1801.04385), Nazanin Alipourfard, Peter G. Fennell, Kristina Lerman 9 | * [Word Translation Without Parallel Data](https://arxiv.org/abs/1710.04087), Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou 10 | -------------------------------------------------------------------------------- /2018-04-11.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Topological Data Analysis](https://arxiv.org/abs/1609.08227), Larry Wasserman 4 | 5 | ## Other suggestions 6 | 7 | * [Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks](https://arxiv.org/abs/1804.03126), Victor Dibia, Çagatay Demiralp 8 | * [Attention is All You Need](http://papers.nips.cc/paper/7181-attention-is-all-you-need), Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin 9 | -------------------------------------------------------------------------------- /2018-04-25.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Stability](https://projecteuclid.org/euclid.bj/1377612862), Bin Yu 4 | 5 | ## Other suggestions 6 | 7 | * [The Marginal Value of Adaptive Gradient Methods in Machine Learning](http://papers.nips.cc/paper/7003-the-marginal-value-of-adaptive-gradient-methods-in-machine-learning), Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern, Nati Srebro, Benjamin Recht 8 | * [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://arxiv.org/abs/1803.03453), Joel Lehman et al. 9 | -------------------------------------------------------------------------------- /2018-05-09.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Bayesians, Frequentists, and Scientists](https://www.researchgate.net/profile/Andrew_Messing/post/Can_anyone_recommend_to_me_a_rigorous_discussion_on_the_difference_between_frequentist_and_Bayesian_interpretations_of_probability/attachment/59d61ddc79197b807797b25c/AS:273743820066822@1442277020944/download/Bayesians%2C+Frequentists%2C+and+Scientists.pdf), Bradley Efron 4 | 5 | ## Other suggestions 6 | 7 | * [Attention Is All You Need](http://papers.nips.cc/paper/7181-attention-is-all-you-need), Ashish Vaswani, Noam Shazee, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin 8 | * [Is Most Published Research Really False?](https://www.annualreviews.org/doi/full/10.1146/annurev-statistics-060116-054104), Jeffrey T. Leek and Leah R. Jager 9 | * [Cluster failure: Why fMRI inferences for spatial extent have inflated false-positive rates](http://www.pnas.org/content/113/28/7900.short), Anders Eklund, Thomas E. Nichols, and Hans Knutsson 10 | * [Equality of Opportunity in Supervised Learning](http://papers.nips.cc/paper/6373-equality-of-opportunity-in-supervised-learning), Moritz Hardt, Eric Price, Nathan Srebro 11 | -------------------------------------------------------------------------------- /2018-05-23.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://arxiv.org/abs/1804.03619), Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, William T. Freeman, Michael Rubinstein \[[blog](https://ai.googleblog.com/2018/04/looking-to-listen-audio-visual-speech.html)\] \[[video](https://www.youtube.com/watch?v=rVQVAPiJWKU)\] \[[webpage](https://looking-to-listen.github.io/)\] 4 | 5 | ## Other suggestions 6 | 7 | * [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://arxiv.org/abs/1804.06437), Juncen Li, Robin Jia, He He, Percy Liang 8 | * [Poincaré Embeddings for Learning Hierarchical Representations](http://papers.nips.cc/paper/7213-poincare-embeddings-for-learning-hierarchical-representations), Maximillian Nickel, Douwe Kiela 9 | * [Attention is All You Need](http://papers.nips.cc/paper/7181-attention-is-all-you-need), Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin 10 | -------------------------------------------------------------------------------- /2018-06-06.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [No Free Lunch Theorems for Optimization](http://georgemaciunas.com/wp-content/uploads/2012/07/Wolpert_NLFoptimization-1.pdf), D.H. Wolpert, W.G. Macready 4 | 5 | ## Other suggestions 6 | 7 | * [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://arxiv.org/abs/1804.06437), Juncen Li, Robin Jia, He He, Percy Liang 8 | * [AutoAugment: Learning Augmentation Policies from Data](https://arxiv.org/abs/1805.09501), Ekin D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, Quoc V. Le 9 | -------------------------------------------------------------------------------- /2018-06-20.md: -------------------------------------------------------------------------------- 1 | # Reading Group Proposals 2 | 3 | ## Chosen paper 4 | 5 | [Probabilistic Numerics and Uncertainty in Computations](https://arxiv.org/abs/1506.01326), Philipp Hennig, Michael A Osborne, Mark Girolami 6 | 7 | ## Other suggestions 8 | 9 | * [Solving the Rubik's Cube Without Human Knowledge](https://arxiv.org/abs/1805.07470), Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi 10 | * [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://arxiv.org/abs/1711.07131), Kuang-Huei Lee, Xiaodong He, Lei Zhang, Linjun Yang 11 | * [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://arxiv.org/abs/1708.08559), Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray 12 | * [Neural scene representation and rendering](http://science.sciencemag.org/content/360/6394/1204.full), S. M. Ali Eslami, Danilo Jimenez Rezende, Frederic Besse, et al. 13 | * [Universal Language Model Fine-tuning for Text Classification](https://arxiv.org/abs/1801.06146), Jeremy Howard, Sebastian Ruder 14 | -------------------------------------------------------------------------------- /2018-07-04.md: -------------------------------------------------------------------------------- 1 | # Reading Group Proposals 2 | 3 | ## Chosen paper 4 | 5 | [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://arxiv.org/abs/1708.08559), Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray 6 | 7 | ## Other suggestions 8 | 9 | * [Continuous control with deep reinforcement learning](https://arxiv.org/abs/1509.02971), Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra 10 | * [DSOS and SDSOS Optimization: More Tractable Alternatives to Sum of Squares and Semidefinite Optimization](https://arxiv.org/abs/1706.02586), Amir Ali Ahmadi, Anirudha Majumdar 11 | * [Gradient-based optimization of neural network architectures](https://openreview.net/forum?id=HkSm8t1PM), Will Grathwohl, Elliot Creager, Seyed Kamyar Seyed Ghasemipour, Richard Zemel 12 | 13 | -------------------------------------------------------------------------------- /2018-07-18.md: -------------------------------------------------------------------------------- 1 | # Reading Group Proposals 2 | 3 | ## Chosen paper 4 | 5 | [Conditional Neural Processes](https://arxiv.org/abs/1807.01613), Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami 6 | 7 | ## Other suggestions 8 | 9 | * [Table-to-text Generation by Structure-aware Seq2seq Learning](https://arxiv.org/abs/1711.09724), Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui 10 | * [Curriculum Learning](http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4701), Yoshua Bengio, Jérôme Louradour, Ronan Collobert, Jason Weston 11 | -------------------------------------------------------------------------------- /2018-08-01.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [A Principled Bayesian Workflow](https://betanalpha.github.io/assets/case_studies/principled_bayesian_workflow.html), Michael Betancourt 4 | 5 | ## Other suggestions 6 | 7 | * [Deep Complex Networks](https://arxiv.org/abs/1705.09792), Chiheb Trabelsi, et al. 8 | * [Image-to-Image Translation with Conditional Adversarial Networks](https://arxiv.org/abs/1611.07004), Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros 9 | * [Adversarial Reprogramming of Neural Networks](https://arxiv.org/abs/1806.11146), Gamaleldin F. Elsayed, Ian Goodfellow, Jascha Sohl-Dickstein 10 | * [This looks like that: deep learning for interpretable image recognition](https://arxiv.org/abs/1806.10574), Chaofan Chen, Oscar Li, Alina Barnett, Jonathan Su, Cynthia Rudin 11 | * [Taking the Human Out of the Loop: A Review of Bayesian Optimization](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7352306), Bobak Shahriari, Kevin Swersky, Ziyu Wang, Ryan P. Adams, and Nando de Freitas 12 | * [Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829), Sara Sabour, Nicholas Frosst, Geoffrey E Hinton 13 | -------------------------------------------------------------------------------- /2018-08-15.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [BPR: Bayesian Personalized Ranking from Implicit Feedback](https://arxiv.org/abs/1205.2618), Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, Lars Schmidt-Thieme 4 | 5 | ## Other suggestions 6 | 7 | * [Image-to-Image Translation with Conditional Adversarial Networks](https://arxiv.org/abs/1611.07004), Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros 8 | * [Yes, but Did It Work?: Evaluating Variational Inference](https://arxiv.org/abs/1802.02538), Yuling Yao, Aki Vehtari, Daniel Simpson, Andrew Gelman 9 | -------------------------------------------------------------------------------- /2018-08-29.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Snorkel: Rapid Training Data Creation with Weak Supervision](https://arxiv.org/abs/1711.10160), Alexander Ratner, Stephen H. Bach, Henry Ehrenberg, Jason Fries, Sen Wu, Christopher Ré 4 | 5 | ## Other suggestions 6 | 7 | * [Factors associated with supermarket and convenience store closure: a discrete time spatial survival modelling approach (paywall)](https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/rssa.12330), Joshua L. Warren, Penny Gordon‐Larsen 8 | * [Deep learning via Hessian-free optimization](http://www.cs.toronto.edu/~jmartens/docs/Deep_HessianFree.pdf), James Martens 9 | * [Neural Combinatorial Optimization with Reinforcement Learning](https://arxiv.org/abs/1611.09940), Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio 10 | -------------------------------------------------------------------------------- /2018-09-12.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation](https://arxiv.org/abs/1809.01587), Minsuk Kahng, Nikhil Thorat, Duen Horng Chau, Fernanda Viégas, Martin Wattenberg 4 | 5 | ## Other suggestions 6 | 7 | * [A Conceptual Introduction to Hamiltonian Monte Carlo](https://arxiv.org/abs/1701.02434), Michael Betancourt 8 | * [Factors associated with supermarket and convenience store closure: a discrete time spatial survival modelling approach (paywall)](https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/rssa.12330), Joshua L. Warren, Penny Gordon‐Larsen 9 | -------------------------------------------------------------------------------- /2018-09-26.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/abs/1612.00593), Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas 4 | 5 | ## Other suggestions 6 | 7 | * [Deep learning of aftershock patterns following large earthquakes](https://www.nature.com/articles/s41586-018-0438-y), Phoebe M. R. DeVries, Fernanda Viégas, Martin Wattenberg & Brendan J. Meade \[[blog](https://www.blog.google/technology/ai/forecasting-earthquake-aftershock-locations-ai-assisted-science/)\] 8 | * [StarSpace: Embed All The Things!](https://arxiv.org/abs/1709.03856), Ledell Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes, Jason Weston 9 | * [Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5791909/), 10 | Justin Cheng, Michael Bernstein, Cristian Danescu-Niculescu-Mizil, and Jure Leskovec 11 | -------------------------------------------------------------------------------- /2018-10-11.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Visual Reinforcement learning with imagined goals](https://arxiv.org/abs/1807.04742), Ashvin Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine 4 | 5 | ## Other suggestions 6 | 7 | * [Semi supervised classification with graph cnns](https://openreview.net/pdf?id=SJU4ayYgl),Thomas N. Kipf, Max Welling 8 | * [Learning dextrous hand manipulation](https://arxiv.org/abs/1808.00177), OpenAI: Marcin Andrychowicz, Bowen Baker, Maciek Chociej, Rafal Jozefowicz, Bob McGrew, Jakub Pachocki, Arthur Petron, Matthias Plappert, Glenn Powell, Alex Ray, Jonas Schneider, Szymon Sidor, Josh Tobin, Peter Welinder, Lilian Weng, Wojciech Zaremba 9 | * [Non‐parametric evidence of second‐leg home advantage in European football.](https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/rssa.12338), Gery Geenens, Thomas Cuddihy 10 | 11 | 12 | 13 | -------------------------------------------------------------------------------- /2018-11-21.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Comprehensive benchmarking of Markov chain Monte Carlo methods for dynamical systems](https://bmcsystbiol.biomedcentral.com/articles/10.1186/s12918-017-0433-1), Benjamin Ballnus, Sabine Hug, Kathrin Hatz, Linus Görlitz, Jan Hasenauer and Fabian J. Theis 4 | 5 | ## Other suggestions 6 | 7 | * [Categorical Reparameterization with Gumbel-Softmax](https://arxiv.org/abs/1611.01144), Eric Jang, Shixiang Gu, Ben Poole 8 | * [Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results](https://journals.sagepub.com/doi/10.1177/2515245917747646), R. Silberzahn, et al. 9 | * [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://arxiv.org/abs/1803.01271), Shaojie Bai, J. Zico Kolter, Vladlen Koltun 10 | -------------------------------------------------------------------------------- /2018-12-05.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [How Does Batch Normalization Help Optimization?](http://papers.nips.cc/paper/7515-how-does-batch-normalization-help-optimization), Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, Aleksander Madry 4 | 5 | ## Other suggestions 6 | 7 | * [On the Dimensionality of Word Embedding](http://papers.nips.cc/paper/7368-on-the-dimensionality-of-word-embedding). Zi Yin, Yuanyuan Shen 8 | * [Review Papers: Modeling Capture, Recapture, and Removal Statistics for Estimation of Demographic Parameters for Fish and Wildlife Populations: Past, Present, and Future](https://www.tandfonline.com/doi/abs/10.1080/01621459.1991.10475022) (paywalled), Kenneth Pollock 9 | * [Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing](https://arxiv.org/abs/1811.03388), Jill-Jênn Vie, Hisashi Kashima 10 | * [Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results](https://journals.sagepub.com/doi/abs/10.1177/2515245917747646), R. Silberzahn, et al. 11 | -------------------------------------------------------------------------------- /2018-12-19.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Neural Ordinary Differential Equations](https://arxiv.org/abs/1806.07366), Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud 4 | 5 | ## Other suggestions 6 | 7 | * [The Matrix Calculus You Need For Deep Learning](https://arxiv.org/abs/1802.01528), Terence Parr, Jeremy Howard 8 | * [Mining of Massive Datasets: Chapter 9 - Recommendation Systems](http://www.mmds.org/), Jure Leskovec, Anand Rajaraman, Jeffrey David Ullman 9 | * [Spinning Up in Deep RL](https://blog.openai.com/spinning-up-in-deep-rl/), OpenAI 10 | * [Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing](https://arxiv.org/abs/1811.03388), Jill-Jênn Vie, Hisashi Kashima 11 | * [Visualizing the Loss Landscape of Neural Nets](https://arxiv.org/abs/1712.09913), Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein 12 | * [How to Start Training: The Effect of Initialization and Architecture](https://arxiv.org/abs/1803.01719), Boris Hanin, David Rolnick 13 | * [Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization](https://openreview.net/forum?id=Bkg9ZeBB37), Wei-Ning Hsu, Yu Zhang, Ron J. Weiss, Yu-An Chung, Yuxuan Wang, Yonghui Wu, James Glass 14 | -------------------------------------------------------------------------------- /2019-01-16.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Auto ML book chapter 3 on neural architecture search](https://www.automl.org/wp-content/uploads/2018/12/nas-1.pdf) 4 | 5 | ## Other suggestions 6 | 7 | * [Learnability can be undecideable](https://www.nature.com/articles/s42256-018-0002-3) 8 | * [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747) 9 | * [Many Analysts, One Datase](https://journals.sagepub.com/doi/10.1177/2515245917747646) 10 | * [AdaNet: Adaptive Structural Learning of Artificial Neural Networks](https://arxiv.org/abs/1607.01097) 11 | -------------------------------------------------------------------------------- /2019-01-30.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [mixup: Beyond Empirical Risk Minimization](https://arxiv.org/abs/1710.09412), Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz 4 | 5 | ## Other suggestions 6 | 7 | * [Causal Reasoning from Meta-reinforcement Learning](https://arxiv.org/abs/1901.08162), Ishita Dasgupta, Jane Wang, Silvia Chiappa, Jovana Mitrovic, Pedro Ortega, David Raposo, Edward Hughes, Peter Battaglia, Matthew Botvinick, Zeb Kurth-Nelson 8 | * [GAN Dissection: Visualizing and Understanding Generative Adversarial Networks](https://arxiv.org/abs/1811.10597), David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba 9 | * [Visualizing the Loss Landscape of Neural Nets](https://arxiv.org/abs/1712.09913), Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein 10 | * [Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results](https://journals.sagepub.com/doi/pdf/10.1177/2515245917747646), R. Silberzahn, et al. 11 | * [Delayed Impact of Fair Machine Learning](https://arxiv.org/abs/1803.04383), Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, Moritz Hardt 12 | -------------------------------------------------------------------------------- /2019-02-13.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Beyond News Contents: The Role of Social Context for Fake News Detection ](https://dl.acm.org/citation.cfm?id=3290994), Kai Shu, Suhang Wang, Huan Liu \[[pdf](http://www.public.asu.edu/~skai2/files/wsdm_2019_fake_news.pdf)\] 4 | 5 | ## Other suggestions 6 | 7 | * [Towards Federated Learning at Scale: System Design](https://arxiv.org/abs/1902.01046), Keith Bonawitz, et al. 8 | * [Learning with Privacy at Scale](https://machinelearning.apple.com/docs/learning-with-privacy-at-scale/appledifferentialprivacysystem.pdf), Differential Privacy Team, Apple \[[blog](https://machinelearning.apple.com/2017/12/06/learning-with-privacy-at-scale.html)\] 9 | -------------------------------------------------------------------------------- /2019-02-27.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Latent Translation: Crossing Modalities by Bridging Generative Models](https://arxiv.org/abs/1902.08261), Yingtao Tian, Jesse Engel 4 | 5 | ## Other suggestions 6 | 7 | * [AutoAugment: Learning Augmentation Policies from Data](https://arxiv.org/abs/1805.09501), Ekin D. Cubuk, Barret Zoph, Dandelion Mané, Vijay Vasudevan, Quoc V. Le 8 | * [Matrix factorization techniques for recommender systems](https://datajobs.com/data-science-repo/Recommender-Systems-[Netflix].pdf), Yehuda Koren, Robert Bell, Chris Volinsky 9 | * [Understanding Hidden Memories of Recurrent Neural Networks](https://arxiv.org/abs/1710.10777), Yao Ming, et al. 10 | -------------------------------------------------------------------------------- /2019-04-08.md: -------------------------------------------------------------------------------- 1 | ## Chosen paper 2 | 3 | [Stochastic blockmodels and community structure in networks](https://journals.aps.org/pre/abstract/10.1103/PhysRevE.83.016107), Brian Karrer and M. E. J. Newman, Phys. Rev. E 83, 2011 4 | 5 | ## Other suggestions 6 | 7 | * [Neural combinatorial optimization with reinforcement learning](https://arxiv.org/abs/1611.09940), Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio 8 | * [Tell me where to look: Guided attention inference](https://arxiv.org/abs/1802.10171), Kunpeng Li, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst, Yun Fu 9 | * [Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results](https://journals.sagepub.com/doi/10.1177/2515245917747646 ), R. Silberzahn, et al. 10 | -------------------------------------------------------------------------------- /2020.md: -------------------------------------------------------------------------------- 1 | # List of Selected Reserahc Papers for Meetings - 2020 2 | 3 | -------------------------------------------------------------------------------- /2021.md: -------------------------------------------------------------------------------- 1 | # List of Selected Reserahc Papers for Meetings - 2021 2 | 3 | -------------------------------------------------------------------------------- /2022-11-01.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [Operationalizing Machine Learning: An Interview Study](https://arxiv.org/abs/2209.09125): Shreya Shankar, Rolando Garcia, Joseph M. Hellerstein, Aditya G. Parameswaran, Sep.2022 3 | 4 | ## Other Suggestion 5 | * [YouTube - Debugging ML in Production feat. Shreya Shankar | Stanford MLSys Seminar Episode 12](https://www.youtube.com/watch?v=aGzu7nI8IRE) 6 | * [Comparing Privacy Laws: GDPR vs CCPA](https://github.com/learn-data-science/data-science-reading/blob/master/Other%20Reference%20Materials/GDPR_CCPA_Comparison-Guide.pdf) 7 | * [Wikipedia - MAXQDA](https://en.wikipedia.org/wiki/MAXQDA) 8 | 9 | 10 | -------------------------------------------------------------------------------- /2022-11-15.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [Designing Theory-Driven User-Centric Explainable AI](https://www.researchgate.net/publication/330967106_Designing_Theory-Driven_User-Centric_Explainable_AI): Danding Wang, Qian Yang, Ashraf Abdul, Brian Y. Lim, May 2019 3 | * Supplementary Materials: 4 | * Porject Website: https://ubiquitous.comp.nus.edu.sg/wp-content/uploads/2019/04/chi2019-xai-framework-tutorial.html 5 | * Project YouTube: https://www.youtube.com/watch?v=RS7jP-6AHck 6 | 7 | ## Other Suggestion 8 | * [GitHub - Machine Learning Interpretability](https://github.com/jphall663/awesome-machine-learning-interpretability) 9 | * [YouTube - Explainable AI explained! | #1 Introduction](https://www.youtube.com/watch?v=OZJ1IgSgP9E) 10 | * [YouTube - Explainable AI explained! | #5 Counterfactual explanations and adversarial attacks](https://www.youtube.com/watch?v=UUZxRct8rIk&list=PLV8yxwGOxvvovp-j6ztxhF3QcKXT6vORU&index=6) 11 | 12 | -------------------------------------------------------------------------------- /2022-11-29.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [Monolith: Real Time Recommendation System With Collisionless Embedding Table](https://arxiv.org/abs/2209.07663): Zhuoran Liu, Leqi Zou, Xuan Zou, Caihua Wang, Biao Zhang, Da Tang, Bolin Zhu, Yijie Zhu, Peng Wu, Ke Wang, Youlong Cheng, Sep.2022 3 | * Supplementary GitHub: https://github.com/Y2Z/monolith 4 | 5 | ## Other Suggestion 6 | * [YouTube - How does YouTube recommend videos? - AI EXPLAINED!](https://www.youtube.com/watch?v=wDxTWp3KMMs) 7 | * [YouTube - RecSys 2016: Paper Session 6 - Deep Neural Networks for YouTube Recommendations](https://www.youtube.com/watch?v=WK_Nr4tUtl8) 8 | * [Deep Neural Networks for Youtube Rec.pdf](https://github.com/learn-data-science/data-science-reading/blob/master/Other%20Reference%20Materials/Deep%20Neural%20Networks%20for%20Youtube%20Rec.pdf): Paul Covington, Jay Adams, Emre Sargin (Google), Sep.2016 9 | * [Breaking apart the monolith ](https://github.com/readme/guides/maintainer-monolith) 10 | 11 | -------------------------------------------------------------------------------- /2022-12-13.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [The Problem with Metrics is a Fundamental Problem for AI](https://arxiv.org/abs/2002.08512): [Rachel Thomas](https://rachel.fast.ai/), David Uminskys, Feb.2020 3 | 4 | ## Other Suggestion 5 | * [Goodhart Taxonomy](https://www.lesswrong.com/posts/EbFABnst8LsidYs5Y/goodhart-taxonomy): by Scott Garrabrant 6 | * [Challenges of AI](https://www.chathamhouse.org/2022/03/challenges-ai): Chatham House, March 22, 2022 7 | * [The ‘right to an explanation’ under EU data protection law](https://medium.com/golden-data/what-rights-related-to-automated-decision-making-do-individuals-have-under-eu-data-protection-law-76f70370fcd0): Golden Data Law, Feb.22, 2019 8 | * [4 tips for improving the reliability of your AI metrics](https://www.redhat.com/architect/ai-metric-reliability): Red Hat, November 15, 2022 9 | * GitHub for SHAP: https://github.com/slundberg/shap 10 | 11 | -------------------------------------------------------------------------------- /2022_Jan_to_Sep.md: -------------------------------------------------------------------------------- 1 | # List of Selected Reserahc Papers for Meetings - Janaury ~ September 2022 2 | 3 | -------------------------------------------------------------------------------- /2023-01-10.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [Unsupervised Learning From Incomplete Measurements for Inverse Problems](https://arxiv.org/abs/2201.12151): [Julián Tachella](https://tachella.github.io/), Dongdong Chen, Mike Davies, Sep.2022 3 | * Supplementary Materials: 4 | * Project Poster & Video: https://nips.cc/virtual/2022/poster/53334 5 | * Project Summary: https://tachella.github.io/projects/equivariantimaging/ 6 | * [Project Slides](https://github.com/learn-data-science/data-science-reading/blob/master/Other%20Reference%20Materials/neurips22-Slides.pdf) 7 | * Project Code: https://github.com/edongdongchen/MOI 8 | 9 | 10 | ## Other Suggestion 11 | * [YouTube - CVPR 2022 Oral: Robust Equivariant Imaging](https://www.youtube.com/watch?v=27iWnWEbQvA): presented by Dongdong Chen 12 | * [YouTube - Best Student Paper ICASSP'22: Reconstructing billions of photons per second](https://www.youtube.com/watch?v=mD76r-OuNtc): presented by the lead author, Julián Tachella 13 | * [YouTube - Deep Generative models and Inverse Problems](https://www.youtube.com/watch?v=vivXNCMmA9I): presented by Alexandros Dimakis 14 | * GitHub for AmbientGAN: https://github.com/AshishBora/ambient-gan 15 | * Signal Models: 16 | * [Science Direct – Signal Model](https://www.sciencedirect.com/topics/engineering/signal-model) 17 | * [Signals & System - Online Textbook](https://eng.libretexts.org/Bookshelves/Electrical_Engineering/Signal_Processing_and_Modeling) 18 | * [Introduction to Physical Signal Models](https://www.dsprelated.com/freebooks/pasp/Introduction_Physical_Signal_Models.html) 19 | -------------------------------------------------------------------------------- /2023-01-24.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [SIGIR '16 Counterfactual Evaluation and Learning for Search, Recommendation and Ad Placement](https://dl.acm.org/doi/10.1145/2911451.2914803): Thorsten Joachims, Adith Swaminathan; July 2016 3 | * Supplementary Materials: 4 | * SIGIR 2016 Tutorial Website: https://www.cs.cornell.edu/~adith/CfactSIGIR2016/ 5 | 6 | ## Other Suggestion 7 | * [SIGIR 2016 - Other Related Tutorial](https://sites.google.com/cornell.edu/recsys2021tutorial/references?pli=1) 8 | * [Counterfactual Evaluation and Learning for Interactive Systems (KDD2022 Tutorial) 9 | About MeSearch](https://counterfactual-ml.github.io/kdd2022-tutorial/) 10 | 11 | ## Other Nominated Papers 12 | * [Locating and Editing Factual Associations in GPT](https://arxiv.org/abs/2202.05262) 13 | * [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://arxiv.org/abs/2104.13478) 14 | -------------------------------------------------------------------------------- /2023-02-07.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines](https://arxiv.org/abs/2205.11558): 3 | Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta, Raja Marjieh, Michael Y. Hu, Robert D. Hawkins, Nathaniel D. Daw, Jonathan D. Cohen, 4 | Karthik Narasimhan, Thomas L. Griffiths; October 2022 5 | * Supplementary Materials: 6 | * Using natural language and program abstractions to instill human inductive biases in machines: https://openreview.net/forum?id=buXZ7nIqiwE 7 | * Poster: https://neurips.cc/media/PosterPDFs/NeurIPS%202022/2b7b82a7ec6de40781fd6ef338b41892.png?t=1666210850.3645766 8 | 9 | 10 | -------------------------------------------------------------------------------- /2023-03-07.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | * [High-throughput Generative Inference of Large Language Models with a Single GPU](https://arxiv.org/abs/2205.11558](https://github.com/FMInference/FlexGen/blob/f5fbfe66a6a1637935243f2e40a95e7b7dbca213/docs/paper.pdf): 3 | Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher Re, Ion Stoica, Ce Zhang; 4 | 5 | * Supplementary Materials: 6 | * Related Code: https://github.com/FMInference/FlexGen 7 | 8 | 9 | 10 | -------------------------------------------------------------------------------- /2023-10-05.md: -------------------------------------------------------------------------------- 1 | ## Chosen Paper 2 | [Perceiver: General Perception with Iterative Attention](https://arxiv.org/abs/2103.03206) suggested by Dakota 3 | 4 | ### Supplementary Materials 5 | * [Perceiver IO](https://arxiv.org/abs/2107.14795): Perceiver generalized to arbitrary output modalities 6 | * Huggingface release of the related Perceiver IO: https://huggingface.co/blog/perceiver 7 | 8 | 9 | ## Other Suggestions 10 | * [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752) suggested by Lara 11 | * [gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling](https://arxiv.org/abs/2308.07192) suggested by Arnie -------------------------------------------------------------------------------- /Deep Clustering/Cheat sheet for Deep Clustering.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/Deep Clustering/Cheat sheet for Deep Clustering.docx -------------------------------------------------------------------------------- /Deep Clustering/Cheat sheet for Deep Clustering.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/Deep Clustering/Cheat sheet for Deep Clustering.pdf -------------------------------------------------------------------------------- /Gaussian Processes/Gaussian Processes Presentation.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/Gaussian Processes/Gaussian Processes Presentation.pdf -------------------------------------------------------------------------------- /Gaussian Processes/Gaussian Processes Presentation.pptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/Gaussian Processes/Gaussian Processes Presentation.pptx -------------------------------------------------------------------------------- /Gaussian Processes/Readme.md: -------------------------------------------------------------------------------- 1 | Presentation slides for the meetup 2016-10-12 based on: 2 | 3 | [Gaussian processes for time-series modelling](http://rsta.royalsocietypublishing.org/content/371/1984/20110550.short), S. Roberts, M. Osborne, M. Ebden, S. Reece, N. Gibson, S. Aigrain \[[pdf](https://pdfs.semanticscholar.org/4c0c/f51fdcbb1da12f3c7e24479612fc15b9c1d3.pdf)\] 4 | -------------------------------------------------------------------------------- /Other Reference Materials/Deep Neural Networks for Youtube Rec.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/Other Reference Materials/Deep Neural Networks for Youtube Rec.pdf -------------------------------------------------------------------------------- /Other Reference Materials/GDPR_CCPA_Comparison-Guide.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/Other Reference Materials/GDPR_CCPA_Comparison-Guide.pdf -------------------------------------------------------------------------------- /Other Reference Materials/neurips22-Slides.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/Other Reference Materials/neurips22-Slides.pdf -------------------------------------------------------------------------------- /Other Reference Materials/readme.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Data Science Reading 2 | 3 | ## Selected and proposed papers after 2016-10-12 4 | 5 | See [summary of all papers](summary.md) or individual files with the name `YYYY-MM-DD.md`. 6 | 7 | ## Selected papers in 2016 8 | 9 | * [2016](archives_2016.md) 10 | 11 | ## Backgrounders 12 | 13 | * [Deep Clustering](https://github.com/learn-data-science/data-science-reading/tree/master/Deep%20Clustering) 14 | * [Gaussian Processes](https://github.com/learn-data-science/data-science-reading/tree/master/Gaussian%20Processes) 15 | * [Image Processing](https://github.com/learn-data-science/data-science-reading/tree/master/image%20processing) 16 | * [Rating Prediction](https://github.com/learn-data-science/data-science-reading/tree/master/rating%20prediction) 17 | -------------------------------------------------------------------------------- /archives_2016.md: -------------------------------------------------------------------------------- 1 | # 2016 Archives 2 | 3 | - 2016-10-12: [Gaussian processes for time-series modelling](http://rsta.royalsocietypublishing.org/content/371/1984/20110550.short), S. Roberts, M. Osborne, M. Ebden, S. Reece, N. Gibson, S. Aigrain \[[pdf](https://pdfs.semanticscholar.org/4c0c/f51fdcbb1da12f3c7e24479612fc15b9c1d3.pdf)\] 4 | - 2016-09-28: [Boltzmann Machines](http://people.stat.sfu.ca/~dac5/BoltzmannMachines.pdf), Geoffrey Hinton 5 | - 2016-09-14: [XGBoost: A Scalable Tree Boosting System](https://arxiv.org/abs/1603.02754), Tianqi Chen, Carlos Guestrin 6 | - 2016-08-31: [Visualizing Data using t-SNE](http://www.cs.toronto.edu/~hinton/absps/tsne.pdf), Laurens van der Maaten, Geoffrey Hinton 7 | - 2016-08-17: [Big Learning with Bayesian Methods](https://arxiv.org/abs/1411.6370 ), Jun Zhu, Jianfei Chen, Wenbo Hu 8 | - 2016-08-03: [Abandoning Objectives: Evolution through the Search for Novelty Alone](http://eplex.cs.ucf.edu/papers/lehman_ecj11.pdf), Joel Lehman, Kenneth O. Stanley 9 | - 2016-07-20: [POINTWISE: Predicting Points and Valuing Decisions in Real Time with NBA Optical Tracking Data](http://www.lukebornn.com/papers/cervone_ssac_2014.pdf), Dan Cervone, Alexander D’Amour, Luke Bornn, Kirk Goldsberry 10 | - 2016-07-06: [Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records](http://www.nature.com/articles/srep26094), Riccardo Miotto, Li Li, Brian A. Kidd & Joel T. Dudley 11 | - 2016-06-22: [Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation](https://arxiv.org/pdf/1406.1078v3.pdf), Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio 12 | - 2016-06-08: [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/abs/1511.06434), Alec Radford, Luke Metz, Soumith Chintala 13 | - 2016-05-25: [Intriguing properties of neural networks](https://arxiv.org/pdf/1312.6199v4.pdf), Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus 14 | - 2016-05-11: [“Why Should I Trust You?” Explaining the Predictions of Any Classifier](https://arxiv.org/pdf/1602.04938v1.pdf), Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin 15 | - 2016-04-27: [Linear Models: A Useful “Microscope” for Causal Analysis](http://ftp.cs.ucla.edu/pub/stat_ser/r409.pdf), Judea Pearl 16 | - 2016-04-13: [INFERRING CAUSAL IMPACT USING BAYESIAN STRUCTURAL TIME-SERIES MODELS](http://de.arxiv.org/pdf/1506.00356), Kay H. Brodersen, Fabian Gallusser, Jim Koehler, Nicolas Remy and Steven L. Scott 17 | - 2016-03-30: [Mastering the game of Go with deep neural networks and tree search](http://www.willamette.edu/~levenick/cs448/goNature.pdf), David Silver, Aja Huang1, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche,Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu1, Thore Graepel1, Demis Hassabis 18 | - 2016-03-16: [A Neural Algorithm of Artistic Style](https://arxiv.org/pdf/1508.06576v2.pdf), Leon A. Gatys, Alexander S. Ecker, Matthias Bethge 19 | - 2016-03-02: [Probabilistic Methods for Time-Series Analysis](http://www.lancs.ac.uk/~killick/Pub/EckleyFearnheadKillick2010.pdf), Idris A. Eckley, Paul Fearnhead, Rebecca Killick 20 | - 2016-02-17: [Practical recommendations for gradient-based training of deep architectures](https://arxiv.org/abs/1206.5533), Yoshua Bengio 21 | - 2016-01-20: [Expectation propagation as a way of life](https://arxiv.org/pdf/1412.4869v1.pdf), Andrew Gelman, Aki Vehtari, Pasi Jylänki, Christian Robert, Nicolas Chopink, John P. Cunningham 22 | - 2016-01-06: [ 23 | Aggregation for the probabilistic traveling salesman problem](http://www.sciencedirect.com/science/article/pii/S0305054805000808), Ann Melissa Campbell 24 | -------------------------------------------------------------------------------- /image processing/README.md: -------------------------------------------------------------------------------- 1 | [Colorful image colorization paper](https://arxiv.org/abs/1603.08511) on colourizing grayscale pictures automatically, and the 2 | [author's website](http://richzhang.github.io/colorization/) with demos. -------------------------------------------------------------------------------- /image processing/colorful image colorization.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/image processing/colorful image colorization.pdf -------------------------------------------------------------------------------- /paper_list_summarizer.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """Combine individual meetup paper lists into one file.""" 3 | from __future__ import print_function 4 | import glob 5 | from io import open # pylint: disable=redefined-builtin 6 | import time 7 | 8 | 9 | _EXCLUDE_FILES = { 10 | "README.md", 11 | "archives_2016.md", 12 | "summary.md", 13 | "presentation_tips.md"} 14 | _ACCEPTED_PAPER_HEADING = "## Chosen paper" 15 | _OTHER_PAPERS_HEADING = "## Other suggestions" 16 | 17 | 18 | def parse_markdown(markdown_content): 19 | """parse_markdown""" 20 | accepted_match = markdown_content.find(_ACCEPTED_PAPER_HEADING) \ 21 | + len(_ACCEPTED_PAPER_HEADING) 22 | other_suggestions_match = markdown_content.find(_OTHER_PAPERS_HEADING) 23 | 24 | accepted_paper = markdown_content[accepted_match:other_suggestions_match] 25 | suggested_papers = markdown_content[(other_suggestions_match + 26 | len(_OTHER_PAPERS_HEADING)):] 27 | 28 | return accepted_paper.strip(), suggested_papers.strip() 29 | 30 | 31 | def parse_files(files, archive_file=None): 32 | """parse_files""" 33 | try: 34 | with open("summary.md", "w", encoding="utf8") as markdown_file: 35 | output_content = "# Papers suggested to date\n\n" 36 | for ffile in files: 37 | content = open(ffile, "r", encoding="utf8").read() 38 | accepted, suggested = parse_markdown(content) 39 | output_content += "# %s\n\n## Chosen Paper\n%s\n\n" \ 40 | "## Other Suggestions\n%s\n\n" \ 41 | % (ffile[:-3], accepted, suggested) 42 | if archive_file: 43 | archive_content = open(archive_file, "r", encoding="utf8").read() 44 | output_content += archive_content 45 | markdown_file.write(output_content) 46 | except Exception as exc: # pylint: disable=broad-except 47 | print("Bailing. Caught an exception: %s" % exc) 48 | 49 | 50 | def main(): 51 | """Execute from command line.""" 52 | files = [f for f in glob.glob("*.md") if f not in _EXCLUDE_FILES] 53 | # hack: sorts files by date in the title 54 | files.sort(key=lambda x: -time.mktime(time.strptime(x, "%Y-%m-%d.md"))) 55 | parse_files(files, archive_file="archives_2016.md") 56 | 57 | 58 | if __name__ == '__main__': 59 | main() 60 | -------------------------------------------------------------------------------- /presentation_tips.md: -------------------------------------------------------------------------------- 1 | # Preparing a presentation for a Kaggle meetup 2 | 3 | _Obviously, several of the suggestions below are only relevant to in-person presentations. For the moment, we are doing the meetups online through Zoom. The parts to ignore should be fairly obvious._ 4 | 5 | ## Choosing a competition 6 | 7 | - Normally we choose a "real" competition that has ended 8 | - Learner or playground competitions are possible though 9 | - Go to the Kaggle [competitions page](https://www.kaggle.com/competitions) 10 | - Sort by _Latest deadline_ to put the most recent competitons at the top 11 | - Scroll down until you find a competition of interest 12 | - Check that the competition hasn't already been presented and isn't scheduled 13 | - check the [log of past meetups](https://docs.google.com/spreadsheets/d/1dmunY2g2Is-S6PlfKVZy_99zbIGvVD-f4Omu_rcXrLo/edit?usp=sharing) 14 | - check the [pipeline of upcoming meetups](https://docs.google.com/spreadsheets/d/1YOVuiNuKMd6A5QCLNnNXCZX7UxiCL4dKv5bOq8K0gmw/edit?usp=sharing) 15 | 16 | ## Preparing the presentation 17 | 18 | - Plan to present for **one hour**, this will allow for about 15 minutes Q&A during and after the talk 19 | - It's good to have some extra, expendable material in case time runs short 20 | - Check out [Bruce's blog post](https://web.archive.org/web/20190812205708/http://blog.kaggle.com/2017/08/09/learn-data-science-from-kaggle-competition-meetups/) of presentation tips 21 | - One tweak on what it says in that blog post. It says don't try to explain a complicated topic in two minutes. But what we have found is that attendees like it when you pick one specific topic that comes up in a competition (what does AUC mean? what is transposed convolution?) and spend a bit of time to explain it from scratch, for someone who's never heard of it before. 22 | - Here's a list of [winning solutions](https://www.kaggle.com/sudalairajkumar/winning-solutions-of-kaggle-competitions). Not sure how complete it is, but if your competition is there, it will be a big help 23 | - Use a big font where possible--much of the audience is far from the screen 24 | - Google Slides works really well 25 | - you can update right up to the last minute or after the presentation 26 | - everyone will have access to your latest updates 27 | - **Pro tip for using Google Slides:** Install this [Chrome/Firefox extension](https://greasyfork.org/en/scripts/420529-slideshide). 28 | 29 | ## The day before 30 | 31 | - Post your presentation slides, even if unfinished 32 | - attendees appreciate it 33 | - Does your laptop have a _real_ HDMI output? 34 | - Adapters don't work well 35 | - If you don't have HDMI, let the organizers know and we'll figure something out 36 | 37 | ## On the day 38 | 39 | - Bring a mouse if you've got one 40 | - You can use the mouse as a pseudo laser pointer 41 | - Works well for the audience, live stream viewers, and video recording 42 | - Show up at least half an hour before the start (i.e., 6:00pm) 43 | - There are always glitches, this gives us time to fix problems 44 | - Wear a solid color top 45 | - Yes, we're talking about your fashion choices 46 | - Why solid color? Patterns and stripes cause weird Moiré effects in the video. 47 | -------------------------------------------------------------------------------- /rating prediction/README.md: -------------------------------------------------------------------------------- 1 | [Dynamic matrix factorization with social influence](http://arxiv.org/abs/1604.06194), taking preference changes over time and social network influence into account in predicting people's preferences with dynamic matrix factorization. 2 | [Dynamic Matrix Factorization: A State Space Approach](http://arxiv.org/abs/1110.2098) and 3 | [Temporal Matrix Factorization for Tracking Concept Drift in individual User Preferences](http://arxiv.org/abs/1510.05263) are background papers on the same theme. -------------------------------------------------------------------------------- /rating prediction/dynamic matrix factorization/Dynamic matrix factorization with social influence.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/rating prediction/dynamic matrix factorization/Dynamic matrix factorization with social influence.pdf -------------------------------------------------------------------------------- /rating prediction/dynamic matrix factorization/background papers/Dynamic Matrix Factorization- A State Space Approach.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/rating prediction/dynamic matrix factorization/background papers/Dynamic Matrix Factorization- A State Space Approach.pdf -------------------------------------------------------------------------------- /rating prediction/dynamic matrix factorization/background papers/Temporal Matrix Factorization for Tracking Concept Drift in Individual User Preferences.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/learn-data-science/data-science-reading/c44cfffd978de5e7bab5866b8a80b050148ae816/rating prediction/dynamic matrix factorization/background papers/Temporal Matrix Factorization for Tracking Concept Drift in Individual User Preferences.pdf -------------------------------------------------------------------------------- /slides_tips.md: -------------------------------------------------------------------------------- 1 | ### Google Slides pro tips for lightning talks 2 | 1. Automatic slide advance 3 | - *File > Publish to the web... > Auto-advance slides > Every 30 seconds* 4 | - uncheck the box *Start slideshow as soon as the player loads* 5 | - edit the generated URL to replace 30000 with 20000 (for 20 seconds) 6 | 2. Laser pointer without menu popup 7 | - go to full screen 8 | - start the presentation on the intro slide by clicking the play button 9 | - complete the next steps within 20 seconds before the slide advances 10 | - move mouse down to make menu appear, right-click on it, choose *Inspect* 11 | - select and delete the following element 12 | ``` 13 |
15 | ``` 16 | - press L to toggle the laser pointer 17 | - to get the menu bar back, do Ctrl-R to refresh the web page (note: this will stop the auto-advance) 18 | 3. Extra slides 19 | - in film strip, right-click on slide, choose *Skip slide* 20 | - they won't show up as the slides auto-advance 21 | - but they can be seen if you navigate to them manually 22 | -------------------------------------------------------------------------------- /summary.md: -------------------------------------------------------------------------------- 1 | # Papers suggested to date 2 | 3 | # 2019-02-27 4 | 5 | ## Chosen Paper 6 | [Latent Translation: Crossing Modalities by Bridging Generative Models](https://arxiv.org/abs/1902.08261), Yingtao Tian, Jesse Engel 7 | 8 | ## Other Suggestions 9 | * [AutoAugment: Learning Augmentation Policies from Data](https://arxiv.org/abs/1805.09501), Ekin D. Cubuk, Barret Zoph, Dandelion Mané, Vijay Vasudevan, Quoc V. Le 10 | * [Matrix factorization techniques for recommender systems](https://datajobs.com/data-science-repo/Recommender-Systems-[Netflix].pdf), Yehuda Koren, Robert Bell, Chris Volinsky 11 | * [Understanding Hidden Memories of Recurrent Neural Networks](https://arxiv.org/abs/1710.10777), Yao Ming, et al. 12 | 13 | # 2019-02-13 14 | 15 | ## Chosen Paper 16 | [Beyond News Contents: The Role of Social Context for Fake News Detection ](https://dl.acm.org/citation.cfm?id=3290994), Kai Shu, Suhang Wang, Huan Liu \[[pdf](http://www.public.asu.edu/~skai2/files/wsdm_2019_fake_news.pdf)\] 17 | 18 | ## Other Suggestions 19 | * [Towards Federated Learning at Scale: System Design](https://arxiv.org/abs/1902.01046), Keith Bonawitz, et al. 20 | * [Learning with Privacy at Scale](https://machinelearning.apple.com/docs/learning-with-privacy-at-scale/appledifferentialprivacysystem.pdf), Differential Privacy Team, Apple \[[blog](https://machinelearning.apple.com/2017/12/06/learning-with-privacy-at-scale.html)\] 21 | 22 | # 2019-01-30 23 | 24 | ## Chosen Paper 25 | [mixup: Beyond Empirical Risk Minimization](https://arxiv.org/abs/1710.09412), Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz 26 | 27 | ## Other Suggestions 28 | * [Causal Reasoning from Meta-reinforcement Learning](https://arxiv.org/abs/1901.08162), Ishita Dasgupta, Jane Wang, Silvia Chiappa, Jovana Mitrovic, Pedro Ortega, David Raposo, Edward Hughes, Peter Battaglia, Matthew Botvinick, Zeb Kurth-Nelson 29 | * [GAN Dissection: Visualizing and Understanding Generative Adversarial Networks](https://arxiv.org/abs/1811.10597), David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba 30 | * [Visualizing the Loss Landscape of Neural Nets](https://arxiv.org/abs/1712.09913), Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein 31 | * [Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results](https://journals.sagepub.com/doi/pdf/10.1177/2515245917747646), R. Silberzahn, et al. 32 | * [Delayed Impact of Fair Machine Learning](https://arxiv.org/abs/1803.04383), Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, Moritz Hardt 33 | 34 | # 2019-01-16 35 | 36 | ## Chosen Paper 37 | [Auto ML book chapter 3 on neural architecture search](https://www.automl.org/wp-content/uploads/2018/12/nas-1.pdf) 38 | 39 | ## Other Suggestions 40 | * [Learnability can be undecideable](https://www.nature.com/articles/s42256-018-0002-3) 41 | * [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747) 42 | * [Many Analysts, One Datase](https://journals.sagepub.com/doi/10.1177/2515245917747646) 43 | * [AdaNet: Adaptive Structural Learning of Artificial Neural Networks](https://arxiv.org/abs/1607.01097) 44 | 45 | # 2018-12-19 46 | 47 | ## Chosen Paper 48 | [Neural Ordinary Differential Equations](https://arxiv.org/abs/1806.07366), Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud 49 | 50 | ## Other Suggestions 51 | * [The Matrix Calculus You Need For Deep Learning](https://arxiv.org/abs/1802.01528), Terence Parr, Jeremy Howard 52 | * [Mining of Massive Datasets: Chapter 9 - Recommendation Systems](http://www.mmds.org/), Jure Leskovec, Anand Rajaraman, Jeffrey David Ullman 53 | * [Spinning Up in Deep RL](https://blog.openai.com/spinning-up-in-deep-rl/), OpenAI 54 | * [Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing](https://arxiv.org/abs/1811.03388), Jill-Jênn Vie, Hisashi Kashima 55 | * [Visualizing the Loss Landscape of Neural Nets](https://arxiv.org/abs/1712.09913), Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein 56 | * [How to Start Training: The Effect of Initialization and Architecture](https://arxiv.org/abs/1803.01719), Boris Hanin, David Rolnick 57 | * [Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization](https://openreview.net/forum?id=Bkg9ZeBB37), Wei-Ning Hsu, Yu Zhang, Ron J. Weiss, Yu-An Chung, Yuxuan Wang, Yonghui Wu, James Glass 58 | 59 | # 2018-12-05 60 | 61 | ## Chosen Paper 62 | [How Does Batch Normalization Help Optimization?](http://papers.nips.cc/paper/7515-how-does-batch-normalization-help-optimization), Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, Aleksander Madry 63 | 64 | ## Other Suggestions 65 | * [On the Dimensionality of Word Embedding](http://papers.nips.cc/paper/7368-on-the-dimensionality-of-word-embedding). Zi Yin, Yuanyuan Shen 66 | * [Review Papers: Modeling Capture, Recapture, and Removal Statistics for Estimation of Demographic Parameters for Fish and Wildlife Populations: Past, Present, and Future](https://www.tandfonline.com/doi/abs/10.1080/01621459.1991.10475022) (paywalled), Kenneth Pollock 67 | * [Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing](https://arxiv.org/abs/1811.03388), Jill-Jênn Vie, Hisashi Kashima 68 | * [Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results](https://journals.sagepub.com/doi/abs/10.1177/2515245917747646), R. Silberzahn, et al. 69 | 70 | # 2018-11-21 71 | 72 | ## Chosen Paper 73 | [Comprehensive benchmarking of Markov chain Monte Carlo methods for dynamical systems](https://bmcsystbiol.biomedcentral.com/articles/10.1186/s12918-017-0433-1), Benjamin Ballnus, Sabine Hug, Kathrin Hatz, Linus Görlitz, Jan Hasenauer and Fabian J. Theis 74 | 75 | ## Other Suggestions 76 | * [Categorical Reparameterization with Gumbel-Softmax](https://arxiv.org/abs/1611.01144), Eric Jang, Shixiang Gu, Ben Poole 77 | * [Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results](https://journals.sagepub.com/doi/10.1177/2515245917747646), R. Silberzahn, et al. 78 | * [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://arxiv.org/abs/1803.01271), Shaojie Bai, J. Zico Kolter, Vladlen Koltun 79 | 80 | # 2018-10-11 81 | 82 | ## Chosen Paper 83 | [Visual Reinforcement learning with imagined goals](https://arxiv.org/abs/1807.04742), Ashvin Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine 84 | 85 | ## Other Suggestions 86 | * [Semi supervised classification with graph cnns](https://openreview.net/pdf?id=SJU4ayYgl),Thomas N. Kipf, Max Welling 87 | * [Learning dextrous hand manipulation](https://arxiv.org/abs/1808.00177), OpenAI: Marcin Andrychowicz, Bowen Baker, Maciek Chociej, Rafal Jozefowicz, Bob McGrew, Jakub Pachocki, Arthur Petron, Matthias Plappert, Glenn Powell, Alex Ray, Jonas Schneider, Szymon Sidor, Josh Tobin, Peter Welinder, Lilian Weng, Wojciech Zaremba 88 | * [Non‐parametric evidence of second‐leg home advantage in European football.](https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/rssa.12338), Gery Geenens, Thomas Cuddihy 89 | 90 | # 2018-09-26 91 | 92 | ## Chosen Paper 93 | [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/abs/1612.00593), Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas 94 | 95 | ## Other Suggestions 96 | * [Deep learning of aftershock patterns following large earthquakes](https://www.nature.com/articles/s41586-018-0438-y), Phoebe M. R. DeVries, Fernanda Viégas, Martin Wattenberg & Brendan J. Meade \[[blog](https://www.blog.google/technology/ai/forecasting-earthquake-aftershock-locations-ai-assisted-science/)\] 97 | * [StarSpace: Embed All The Things!](https://arxiv.org/abs/1709.03856), Ledell Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes, Jason Weston 98 | * [Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5791909/), 99 | Justin Cheng, Michael Bernstein, Cristian Danescu-Niculescu-Mizil, and Jure Leskovec 100 | 101 | # 2018-09-12 102 | 103 | ## Chosen Paper 104 | [GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation](https://arxiv.org/abs/1809.01587), Minsuk Kahng, Nikhil Thorat, Duen Horng Chau, Fernanda Viégas, Martin Wattenberg 105 | 106 | ## Other Suggestions 107 | * [A Conceptual Introduction to Hamiltonian Monte Carlo](https://arxiv.org/abs/1701.02434), Michael Betancourt 108 | * [Factors associated with supermarket and convenience store closure: a discrete time spatial survival modelling approach (paywall)](https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/rssa.12330), Joshua L. Warren, Penny Gordon‐Larsen 109 | 110 | # 2018-08-29 111 | 112 | ## Chosen Paper 113 | [Snorkel: Rapid Training Data Creation with Weak Supervision](https://arxiv.org/abs/1711.10160), Alexander Ratner, Stephen H. Bach, Henry Ehrenberg, Jason Fries, Sen Wu, Christopher Ré 114 | 115 | ## Other Suggestions 116 | * [Factors associated with supermarket and convenience store closure: a discrete time spatial survival modelling approach (paywall)](https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/rssa.12330), Joshua L. Warren, Penny Gordon‐Larsen 117 | * [Deep learning via Hessian-free optimization](http://www.cs.toronto.edu/~jmartens/docs/Deep_HessianFree.pdf), James Martens 118 | * [Neural Combinatorial Optimization with Reinforcement Learning](https://arxiv.org/abs/1611.09940), Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio 119 | 120 | # 2018-08-15 121 | 122 | ## Chosen Paper 123 | [BPR: Bayesian Personalized Ranking from Implicit Feedback](https://arxiv.org/abs/1205.2618), Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, Lars Schmidt-Thieme 124 | 125 | ## Other Suggestions 126 | * [Image-to-Image Translation with Conditional Adversarial Networks](https://arxiv.org/abs/1611.07004), Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros 127 | * [Yes, but Did It Work?: Evaluating Variational Inference](https://arxiv.org/abs/1802.02538), Yuling Yao, Aki Vehtari, Daniel Simpson, Andrew Gelman 128 | 129 | # 2018-08-01 130 | 131 | ## Chosen Paper 132 | [A Principled Bayesian Workflow](https://betanalpha.github.io/assets/case_studies/principled_bayesian_workflow.html), Michael Betancourt 133 | 134 | ## Other Suggestions 135 | * [Deep Complex Networks](https://arxiv.org/abs/1705.09792), Chiheb Trabelsi, et al. 136 | * [Image-to-Image Translation with Conditional Adversarial Networks](https://arxiv.org/abs/1611.07004), Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros 137 | * [Adversarial Reprogramming of Neural Networks](https://arxiv.org/abs/1806.11146), Gamaleldin F. Elsayed, Ian Goodfellow, Jascha Sohl-Dickstein 138 | * [This looks like that: deep learning for interpretable image recognition](https://arxiv.org/abs/1806.10574), Chaofan Chen, Oscar Li, Alina Barnett, Jonathan Su, Cynthia Rudin 139 | * [Taking the Human Out of the Loop: A Review of Bayesian Optimization](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7352306), Bobak Shahriari, Kevin Swersky, Ziyu Wang, Ryan P. Adams, and Nando de Freitas 140 | * [Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829), Sara Sabour, Nicholas Frosst, Geoffrey E Hinton 141 | 142 | # 2018-07-18 143 | 144 | ## Chosen Paper 145 | [Conditional Neural Processes](https://arxiv.org/abs/1807.01613), Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami 146 | 147 | ## Other Suggestions 148 | * [Table-to-text Generation by Structure-aware Seq2seq Learning](https://arxiv.org/abs/1711.09724), Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui 149 | * [Curriculum Learning](http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4701), Yoshua Bengio, Jérôme Louradour, Ronan Collobert, Jason Weston 150 | 151 | # 2018-07-04 152 | 153 | ## Chosen Paper 154 | [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://arxiv.org/abs/1708.08559), Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray 155 | 156 | ## Other Suggestions 157 | * [Continuous control with deep reinforcement learning](https://arxiv.org/abs/1509.02971), Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra 158 | * [DSOS and SDSOS Optimization: More Tractable Alternatives to Sum of Squares and Semidefinite Optimization](https://arxiv.org/abs/1706.02586), Amir Ali Ahmadi, Anirudha Majumdar 159 | * [Gradient-based optimization of neural network architectures](https://openreview.net/forum?id=HkSm8t1PM), Will Grathwohl, Elliot Creager, Seyed Kamyar Seyed Ghasemipour, Richard Zemel 160 | 161 | # 2018-06-20 162 | 163 | ## Chosen Paper 164 | [Probabilistic Numerics and Uncertainty in Computations](https://arxiv.org/abs/1506.01326), Philipp Hennig, Michael A Osborne, Mark Girolami 165 | 166 | ## Other Suggestions 167 | * [Solving the Rubik's Cube Without Human Knowledge](https://arxiv.org/abs/1805.07470), Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi 168 | * [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://arxiv.org/abs/1711.07131), Kuang-Huei Lee, Xiaodong He, Lei Zhang, Linjun Yang 169 | * [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://arxiv.org/abs/1708.08559), Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray 170 | * [Neural scene representation and rendering](http://science.sciencemag.org/content/360/6394/1204.full), S. M. Ali Eslami, Danilo Jimenez Rezende, Frederic Besse, et al. 171 | * [Universal Language Model Fine-tuning for Text Classification](https://arxiv.org/abs/1801.06146), Jeremy Howard, Sebastian Ruder 172 | 173 | # 2018-06-06 174 | 175 | ## Chosen Paper 176 | [No Free Lunch Theorems for Optimization](http://georgemaciunas.com/wp-content/uploads/2012/07/Wolpert_NLFoptimization-1.pdf), D.H. Wolpert, W.G. Macready 177 | 178 | ## Other Suggestions 179 | * [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://arxiv.org/abs/1804.06437), Juncen Li, Robin Jia, He He, Percy Liang 180 | * [AutoAugment: Learning Augmentation Policies from Data](https://arxiv.org/abs/1805.09501), Ekin D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, Quoc V. Le 181 | 182 | # 2018-05-23 183 | 184 | ## Chosen Paper 185 | [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://arxiv.org/abs/1804.03619), Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, William T. Freeman, Michael Rubinstein \[[blog](https://ai.googleblog.com/2018/04/looking-to-listen-audio-visual-speech.html)\] \[[video](https://www.youtube.com/watch?v=rVQVAPiJWKU)\] \[[webpage](https://looking-to-listen.github.io/)\] 186 | 187 | ## Other Suggestions 188 | * [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://arxiv.org/abs/1804.06437), Juncen Li, Robin Jia, He He, Percy Liang 189 | * [Poincaré Embeddings for Learning Hierarchical Representations](http://papers.nips.cc/paper/7213-poincare-embeddings-for-learning-hierarchical-representations), Maximillian Nickel, Douwe Kiela 190 | * [Attention is All You Need](http://papers.nips.cc/paper/7181-attention-is-all-you-need), Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin 191 | 192 | # 2018-05-09 193 | 194 | ## Chosen Paper 195 | [Bayesians, Frequentists, and Scientists](https://www.researchgate.net/profile/Andrew_Messing/post/Can_anyone_recommend_to_me_a_rigorous_discussion_on_the_difference_between_frequentist_and_Bayesian_interpretations_of_probability/attachment/59d61ddc79197b807797b25c/AS:273743820066822@1442277020944/download/Bayesians%2C+Frequentists%2C+and+Scientists.pdf), Bradley Efron 196 | 197 | ## Other Suggestions 198 | * [Attention Is All You Need](http://papers.nips.cc/paper/7181-attention-is-all-you-need), Ashish Vaswani, Noam Shazee, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin 199 | * [Is Most Published Research Really False?](https://www.annualreviews.org/doi/full/10.1146/annurev-statistics-060116-054104), Jeffrey T. Leek and Leah R. Jager 200 | * [Cluster failure: Why fMRI inferences for spatial extent have inflated false-positive rates](http://www.pnas.org/content/113/28/7900.short), Anders Eklund, Thomas E. Nichols, and Hans Knutsson 201 | * [Equality of Opportunity in Supervised Learning](http://papers.nips.cc/paper/6373-equality-of-opportunity-in-supervised-learning), Moritz Hardt, Eric Price, Nathan Srebro 202 | 203 | # 2018-04-25 204 | 205 | ## Chosen Paper 206 | [Stability](https://projecteuclid.org/euclid.bj/1377612862), Bin Yu 207 | 208 | ## Other Suggestions 209 | * [The Marginal Value of Adaptive Gradient Methods in Machine Learning](http://papers.nips.cc/paper/7003-the-marginal-value-of-adaptive-gradient-methods-in-machine-learning), Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern, Nati Srebro, Benjamin Recht 210 | * [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://arxiv.org/abs/1803.03453), Joel Lehman et al. 211 | 212 | # 2018-04-11 213 | 214 | ## Chosen Paper 215 | [Topological Data Analysis](https://arxiv.org/abs/1609.08227), Larry Wasserman 216 | 217 | ## Other Suggestions 218 | * [Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks](https://arxiv.org/abs/1804.03126), Victor Dibia, Çagatay Demiralp 219 | * [Attention is All You Need](http://papers.nips.cc/paper/7181-attention-is-all-you-need), Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin 220 | 221 | # 2018-03-28 222 | 223 | ## Chosen Paper 224 | [Self-Normalizing Neural Networks](https://arxiv.org/abs/1706.02515), Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter 225 | 226 | ## Other Suggestions 227 | * [Improving Generalization Performance by Switching from Adam to SGD](https://arxiv.org/abs/1712.07628), Nitish Shirish Keskar, Richard Socher 228 | * [Can you Trust the Trend: Discovering Simpson's Paradoxes in Social Data](https://arxiv.org/abs/1801.04385), Nazanin Alipourfard, Peter G. Fennell, Kristina Lerman 229 | * [Word Translation Without Parallel Data](https://arxiv.org/abs/1710.04087), Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou 230 | 231 | # 2018-03-14 232 | 233 | ## Chosen Paper 234 | [Deep Image Prior](https://arxiv.org/abs/1711.10925), Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky \[[blog](https://dmitryulyanov.github.io/deep_image_prior)\] \[[supplementary material](https://box.skoltech.ru/index.php/s/ib52BOoV58ztuPM#pdfviewer)\] \[[code](https://github.com/DmitryUlyanov/deep-image-prior)\] 235 | 236 | ## Other Suggestions 237 | * [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://arxiv.org/abs/1803.03453), Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Julie Beaulieu, Peter J. Bentley, Samuel Bernard, Guillaume Belson, David M. Bryson, Nick Cheney, Antoine Cully, Stephane Donciuex, Fred C. Dyer, Kai Olav Ellefsen, Robert Feldt, Stephan Fischer, Stephanie Forrest, Antoine Frénoy, Christian Gagneé, Leni Le Goff, Laura M. Grabowski, Babak Hodjat, Laurent Keller, Carole Knibbe, Peter Krcah, Richard E. Lenski, Hod Lipson, Robert MacCurdy, Carlos Maestre, Risto Miikkulainen, Sara Mitri, David E. Moriarty, Jean-Baptiste Mouret, Anh Nguyen, Charles Ofria, Marc Parizeau, David Parsons, Robert T. Pennock, William F. Punch, Thomas S. Ray, Marc Schoenauer, Eric Shulte, Karl Sims, Kenneth O. Stanley, François Taddei, Danesh Tarapore, Simon Thibault, Westley Weimer, Richard Watson, et al. (1 additional author not shown) 238 | * [Distilling a Neural Network Into a Soft Decision Tree](https://arxiv.org/abs/1711.09784), Nicholas Frosst, Geoffrey Hinton 239 | 240 | # 2018-02-28 241 | 242 | ## Chosen Paper 243 | [Distilling the Knowledge in a Neural Network](https://arxiv.org/abs/1503.02531), Geoffrey Hinton, Oriol Vinyals, Jeff Dean 244 | 245 | ## Other Suggestions 246 | * [Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings](https://arxiv.org/abs/1712.06961), Hanan Aldarmaki, Mahesh Mohan, Mona Diab 247 | * [The philosophy of Bayes factors and the quantification of statistical evidence](https://www.sciencedirect.com/science/article/pii/S0022249615000723), Richard D. Morey, Jan-Willem Romeijn, Jeffrey N. Rouder 248 | * [The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets](https://arxiv.org/abs/1802.08232), Nicholas Carlini, Chang Liu, Jernej Kos, Úlfar Erlingsson, Dawn Song 249 | 250 | # 2018-01-31 251 | 252 | ## Chosen Paper 253 | [Missing-data imputation](http://www.stat.columbia.edu/~gelman/arm/missing.pdf), Andrew Gelman and Jennifer Hill 254 | 255 | ## Other Suggestions 256 | * [Hybrid computing using a neural network with dynamic external memory](https://ora.ox.ac.uk/objects/uuid:dd8473bd-2d70-424d-881b-86d9c9c66b51/datastreams/bine2aea0d2-0f9c-43a5-b551-c9570284d9f0), A Graves, G Wayne, M Reynolds, T Harley, I Danihelka 257 | * [Spherical CNNS](https://openreview.net/pdf?id=Hkbd5xZRb), Taco S. Cohen, Mario Geiger, Jonas Köhler, Max Welling 258 | * [You Only Look Once: Unified, Real-Time Object Detection](https://arxiv.org/abs/1506.02640), Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi 259 | 260 | # 2018-01-17 261 | 262 | ## Chosen Paper 263 | [Probabilistic record linkage](https://academic.oup.com/ije/article-lookup/doi/10.1093/ije/dyv322), Adrian Sayers, Yoav Ben-Shlomo, Ashley W Blom and Fiona Steele 264 | 265 | ## Other Suggestions 266 | * [You Only Look Once: Unified, Real-Time Object Detection](https://arxiv.org/abs/1506.02640), Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi 267 | * [Virtual Adversarial Ladder Networks For Semi-supervised Learning](https://arxiv.org/abs/1711.07476), Saki Shinoda, Daniel E. Worrall, Gabriel J. Brostow 268 | * [Equation-free mechanistic ecosystem forecasting using empirical dynamic modeling](http://www.pnas.org/content/112/13/E1569.long), Hao Ye, Richard J. Beamish, Sarah M. Glaser, Sue C. H. Grant, Chih-hao Hsieh, Laura J. Richards, Jon T. Schnute and George Sugihara 269 | * [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://arxiv.org/abs/1712.01815), David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis 270 | * [Character-level Convolutional Networks for Text Classification](http://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classifica), Xiang Zhang, Junbo Zhao, Yann LeCun 271 | 272 | # 2018-01-03 273 | 274 | ## Chosen Paper 275 | [PD-Sparse : A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification](http://proceedings.mlr.press/v48/yenb16.pdf), Ian E. H. Yen, Xiangru Huang, Kai Zhong, Pradeep Ravikumar, Inderjit S. Dhillon 276 | 277 | ## Other Suggestions 278 | * [DeepZip: Lossless Compression using Recurrent Networks](https://pdfs.semanticscholar.org/6a70/3b8be6db81af05628ff6897feb6bf8940a8d.pdf), Kedar Tatwawadi 279 | * [Equation-free mechanistic ecosystem forecasting using empirical dynamic modeling](http://www.pnas.org/content/112/13/E1569.long), Hao Ye, Richard J. Beamish, Sarah M. Glaser, Sue C. H. Grant, Chih-hao Hsieh, Laura J. Richards, Jon T. Schnute and George Sugihara 280 | * [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://arxiv.org/abs/1712.01815), David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis 281 | 282 | # 2017-12-06 283 | 284 | ## Chosen Paper 285 | [Opening the Black Box of Deep Neural Networks via Information](https://arxiv.org/abs/1703.00810), Ravid Shwartz-Ziv, Naftali Tishby 286 | 287 | ## Other Suggestions 288 | * [Understanding deep learning requires rethinking generalization](https://arxiv.org/abs/1611.03530), Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals 289 | * [Transformation invariant and outlier revealing dimensionality reduction using triplet embedding](https://pdfs.semanticscholar.org/4f45/7460407241fc4872dd7bfaad7771e6a4b081.pdf), Ehsan Amid, Manfred K. Warmuth 290 | * [When to conduct probabilistic linkage vs. deterministic linkage? A simulation study](https://www.sciencedirect.com/science/article/pii/S1532046415000921), Y Zhu, Y Matsuyama, Y Ohashi, S Setoguchi 291 | * [Word Translation Without Parallel Data](https://arxiv.org/abs/1710.04087), Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou 292 | * [Learning Transferable Architectures for Scalable Image Recognition](https://arxiv.org/abs/1707.07012), Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le 293 | 294 | # 2017-11-22 295 | 296 | ## Chosen Paper 297 | [Solving a Higgs optimization problem with quantum annealing for machine learning](https://www.nature.com/articles/nature24047), Alex Mott, Joshua Job, Jean-Roch Vlimant, Daniel Lidar & Maria Spiropulu 298 | 299 | ## Other Suggestions 300 | * [Bayesian Inference for Assessing Effects of Email Marketing Campaigns](https://dash.harvard.edu/bitstream/handle/1/28552972/Wu_Li_Liu2016.pdf?sequence=4), Wu, Jiexing, Kate J. Li, and Jun S. Liu 301 | * [Why Neurons Have Thousands of Synapses, a Theory of Sequence Memory in Neocortex](https://www.frontiersin.org/articles/10.3389/fncir.2016.00023/full), Jeff Hawkins and Subutai Ahmad 302 | * [Matrix capsules with EM routing](https://openreview.net/forum?id=HJWLfGWRb), Geoffrey E Hinton, Sara Sabour, Nicholas Frosst 303 | * [End-To-End Memory Networks](http://papers.nips.cc/paper/5846-end-to-end-memory-networks), Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus 304 | 305 | # 2017-11-08 306 | 307 | ## Chosen Paper 308 | [Dynamic Routing Between Capsules](http://papers.nips.cc/paper/6975-dynamic-routing-between-capsules), Sara Sabour, Nicholas Frosst, Geoffrey E. Hinton 309 | 310 | ## Other Suggestions 311 | * [Word Translation Without Parallel Data](https://arxiv.org/abs/1710.04087), Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou 312 | * [Practical Bayesian Inference for Record Linkage](https://arxiv.org/abs/1710.10558), Brendan S. McVeigh, Jared S. Murray 313 | * [Deep Illumination: Approximating Dynamic Global Illumination with Generative Adversarial Network](https://arxiv.org/abs/1710.09834), Manu Mathew Thomas, Angus G. Forbes 314 | * [WaveNet: A Generative Model for Raw Audio](https://arxiv.org/abs/1609.03499), Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, Koray Kavukcuoglu 315 | * [Conditional Random Fields as Recurrent Neural Networks](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zheng_Conditional_Random_Fields_ICCV_2015_paper.pdf), Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet, Zhizhong Su3 Dalong Du, Chang Huang, Philip H. S. Torr 316 | 317 | # 2017-10-25 318 | 319 | ## Chosen Paper 320 | [Speech Enhancement Using Bayesian Wavenet](https://pdfs.semanticscholar.org/1031/1242b016349ba14b56b5554353cf820985c9.pdf), Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Dinei Florencio, Mark Hasegawa-Johnson \[[code](https://github.com/auspicious3000/WaveNet-Enhancement)\] 321 | 322 | ## Other Suggestions 323 | * [Age Progression/Regression by Conditional Adversarial Autoencoder](https://arxiv.org/abs/1702.08423), Zhifei Zhang, Yang Song, Hairong Qi 324 | * [Trust in numbers](http://www.rss.org.uk/Images/PDF/events/2017/President's-address-June-2017.pdf), David Spiegelhalter 325 | * [Training recurrent networks online without backtracking](https://arxiv.org/abs/1507.07680), Yann Ollivier, Corentin Tallec, Guillaume Charpiat 326 | * [Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion](https://www.cs.cmu.edu/~nlao/publication/2014.kdd.pdf), Xin Luna Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, Wei Zhang 327 | * [Perturbations in Epidemiological Models: When zombies attack, we can survive!](http://www.tandfonline.com/doi/pdf/10.1080/23737867.2014.11414478), Robert F. Allen, Cassandra Jens & Theodore J. Wendt 328 | 329 | # 2017-10-11 330 | 331 | ## Chosen Paper 332 | [If correlation doesn’t imply causation, then what does?](http://www.michaelnielsen.org/ddi/if-correlation-doesnt-imply-causation-then-what-does/), Michael Nielsen 333 | 334 | ## Other Suggestions 335 | * [Multi-Scale Context Aggregation by Dilated Convolutions](https://arxiv.org/abs/1511.07122), Fisher Yu, Vladlen Koltun 336 | * [Perturbations in Epidemiological Models: When zombies attack, we can survive!](http://www.tandfonline.com/doi/pdf/10.1080/23737867.2014.11414478), Robert F. Allen, Cassandra Jens & Theodore J. Wendt 337 | 338 | # 2017-09-27 339 | 340 | ## Chosen Paper 341 | [Evidence of bias in the Eurovision song contest: modelling the votes using Bayesian hierarchical models](https://arxiv.org/abs/1308.6312), Marta Blangiardo, Gianluca Baio 342 | 343 | ## Other Suggestions 344 | * [Data Programming: Creating Large Training Sets, Quickly](https://arxiv.org/abs/1605.07723), Ratner, De Sa, Wu, Selsam, Ré 345 | * [“Why Should I Trust You?” Explaining the Predictions of Any Classifier](https://arxiv.org/pdf/1602.04938v1.pdf), Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin 346 | * [Opening the Black Box of Deep Neural Networks via Information](https://arxiv.org/abs/1703.00810), Ravid Shwartz-Ziv, Naftali Tishby 347 | 348 | # 2017-09-13 349 | 350 | ## Chosen Paper 351 | [Learning to learn by gradient descent by gradient descent](http://papers.nips.cc/paper/6461-learning-to-learn-by-gradient-descent-by-gradient-descent.pdf), Marcin Andrychowicz, Misha Denil, Sergio Gómez Colmenarejo, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas 352 | 353 | ## Other Suggestions 354 | * [Evidence of bias in the Eurovision song contest: modelling the votes using Bayesian hierarchical models](http://www.tandfonline.com/doi/full/10.1080/02664763.2014.909792), Marta Blangiardo, Gianluca Baio 355 | * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://arxiv.org/abs/1502.03167), Sergey Ioffe, Christian Szegedy 356 | * [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://arxiv.org/abs/1708.06733), Tianyu Gu, Brendan Dolan-Gavitt, Siddharth Garg 357 | * [Attentive Recurrent Comparators](https://arxiv.org/abs/1703.00767), Pranav Shyam, Shubham Gupta, Ambedkar Dukkipati 358 | 359 | # 2017-08-30 360 | 361 | ## Chosen Paper 362 | [A Brief Survey of Deep Reinforcement Learning](https://arxiv.org/abs/1708.05866), Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath 363 | 364 | ## Other Suggestions 365 | * [Methodologies for Cross-Domain Data Fusion: An Overview](http://ieeexplore.ieee.org/abstract/document/7230259/), Yu Zheng \[[pdf](https://pdfs.semanticscholar.org/fe9d/375dd02a8504b7c5c011e3696e6e6f63f537.pdf)\] 366 | * [Transitive Invariance for Self-supervised Visual Representation Learning](https://arxiv.org/abs/1708.02901), Xiaolong Wang, Kaiming He, Abhinav Gupta 367 | * [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747), Sebastian Ruder 368 | * [Engineering Efficient and Effective Non-Metric Space Library](https://www.researchgate.net/profile/Leonid_Boytsov/publication/275023439_Engineering_Efficient_and_Effective_Non-metric_Space_Library/links/552ec83d0cf2acd38cbbd828.pdf), Leonid Boytsov and Bilegsaikhan Naidan 369 | 370 | # 2017-08-16 371 | 372 | ## Chosen Paper 373 | [Variational Inference: A Review for Statisticians](https://arxiv.org/abs/1601.00670), David M. Blei, Alp Kucukelbir, Jon D. McAuliffe 374 | 375 | ## Other Suggestions 376 | * [Challenges in Data-to-Document Generation](https://arxiv.org/abs/1707.08052), Sam Wiseman, Stuart M. Shieber, Alexander M. Rush 377 | * [Transitive Invariance for Self-supervised Visual Representation Learning](https://arxiv.org/abs/1708.02901), Xiaolong Wang, Kaiming He, Abhinav Gupta 378 | * [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747), Sebastian Ruder 379 | * [Engineering Efficient and Effective Non-Metric Space Library](https://www.researchgate.net/profile/Leonid_Boytsov/publication/275023439_Engineering_Efficient_and_Effective_Non-metric_Space_Library/links/552ec83d0cf2acd38cbbd828.pdf), Leonid Boytsov and Bilegsaikhan Naidan 380 | 381 | # 2017-08-02 382 | 383 | ## Chosen Paper 384 | [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://arxiv.org/abs/1706.05125), Lewis, Yarats, Dauphin, Parikh, Batra \[[blog](https://code.facebook.com/posts/1686672014972296/deal-or-no-deal-training-ai-bots-to-negotiate/)\] \[[code](https://github.com/facebookresearch/end-to-end-negotiator)\] 385 | 386 | ## Other Suggestions 387 | * [Data Programming: Creating Large Training Sets, Quickly](https://arxiv.org/abs/1605.07723), Ratner, De Sa, Wu, Selsam, Ré 388 | * [BIRDNEST: Bayesian Inference for Ratings-Fraud Detection](https://arxiv.org/abs/1511.06030), Hooi, Shah, Beutel, Gunnemann, Akoglu, Kumar, Makhija, Faloutsos 389 | * [Stealing Machine Learning Models via Prediction APIs](https://www.usenix.org/system/files/conference/usenixsecurity16/sec16_paper_tramer.pdf), Tramèr, Zhang, Juels, Reiter, Ristenpart \[[slides](https://www.usenix.org/sites/default/files/conference/protected-files/security16_slides_tramer.pdf)\] \[[code](https://github.com/ftramer/Steal-ML)\] [\[video](https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/tramer)\] 390 | 391 | # 2017-07-19 392 | 393 | ## Chosen Paper 394 | [Tutorial on Variational Autoencoders](https://arxiv.org/abs/1606.05908), Carl Doersch 395 | 396 | ## Other Suggestions 397 | * [Data Programming: Creating Large Training Sets, Quickly](https://arxiv.org/abs/1605.07723), Alexander Ratner, Christopher De Sa, Sen Wu, Daniel Selsam, Christopher Ré 398 | * [Climbing the Kaggle Leaderboard by Exploiting the Log-Loss Oracle](https://arxiv.org/abs/1707.01825), Jacob Whitehill 399 | 400 | # 2017-07-05 401 | 402 | ## Chosen Paper 403 | [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://arxiv.org/abs/1703.04977), Alex Kendall, Yarin Gal 404 | 405 | ## Other Suggestions 406 | * [Surprise Search: Beyond Objectives and Novelty](http://antoniosliapis.com/papers/surprise_search_beyond_objectives_and_novelty.pdf), Daniele Gravina, Antonios Liapis, Georgios N. Yannakakis 407 | * [Two Decades of Recommender Systems at Amazon.com](http://ieeexplore.ieee.org/abstract/document/7927889/), Brent Smith, Greg Linden 408 | * [Data Programming: Creating Large Training Sets, Quickly](http://papers.nips.cc/paper/6523-data-programming-creating-large-training-sets-quickly), Alexander J. Ratner, Christopher M. De Sa, Sen Wu, Daniel Selsam, Christopher Ré 409 | 410 | # 2017-06-21 411 | 412 | ## Chosen Paper 413 | [Introduction to Nonnegative Matrix Factorization](https://pdfs.semanticscholar.org/377f/81ef8f46f8f26e565a6a379cac6cae31f68f.pdf), Nicolas Gillis 414 | 415 | ## Other Suggestions 416 | * [Collaborative Filtering for Implicit Feedback Datasets](http://yifanhu.net/PUB/cf.pdf), Yifan Hu, Yehuda Koren, Chris Volinsky 417 | * [Manifold Relevance Determination](https://arxiv.org/abs/1206.4610), Andreas Damianou, Carl Ek, Michalis Titsias, Neil Lawrence 418 | * [DART: Dropouts meet Multiple Additive Regression Trees](http://proceedings.mlr.press/v38/korlakaivinayak15.pdf), K. V. Rashmi, Ran Gilad-Bachrach 419 | * [Count-ception: Counting by Fully Convolutional Redundant Counting](https://arxiv.org/abs/1703.08710), Joseph Paul Cohen, Henry Z. Lo, Yoshua Bengio 420 | 421 | # 2017-06-07 422 | 423 | ## Chosen Paper 424 | [Pixel Recurrent Neural Networks](https://arxiv.org/abs/1601.06759), Aäron van den Oord, Nal Kalchbrenner, Koray Kavukcuoglu \[[notes](http://singsoftnext.com/pixel-recurrent-neural-networks/)\] 425 | 426 | ## Other Suggestions 427 | * [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993), Gao Huang, Zhuang Liu, Kilian Q. Weinberger, Laurens van der Maaten 428 | * [Large-Scale Evolution of Image Classifiers](https://arxiv.org/abs/1703.01041), Esteban Real, Sherry Moore, Andrew Selle, Saurabh Saxena, Yutaka Leon Suematsu, Jie Tan, Quoc Le, Alex Kurakin 429 | 430 | # 2017-05-24 431 | 432 | ## Chosen Paper 433 | [Constraints versus priors](https://www.stat.berkeley.edu/~stark/Preprints/constraintsPriors15.pdf), Philip B. Stark 434 | 435 | ## Other Suggestions 436 | * [Modelling illegal drug participation](http://onlinelibrary.wiley.com/doi/10.1111/rssa.12252/full), Sarah Brown, Mark N. Harris, Preety Srivastava, Xiaohui Zhang 437 | * [Learning to learn by gradient descent by gradient descent](http://papers.nips.cc/paper/6461-learning-to-learn-by-gradient-descent-by-gradient-descent), Marcin Andrychowicz, Misha Denil, Sergio Gómez Colmenarejo, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas 438 | * [ML confidential: machine learning on encrypted data](http://cryptosith.org/papers/mlconf-20130212.pdf), Thore Graepel, Kristin Lauter, and Michael Naehrig 439 | * [Using stacking to average Bayesian predictive distributions](https://arxiv.org/abs/1704.02030), Yuling Yao, Aki Vehtari, Daniel Simpson, Andrew Gelman 440 | 441 | # 2017-05-10 442 | 443 | ## Chosen Paper 444 | [Semi-supervised knowledge transfer for deep learning from private training data](https://arxiv.org/abs/1610.05755), Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal Talwar 445 | 446 | ## Other Suggestions 447 | * [Collaborative filtering for implicit feedback datasets](http://ieeexplore.ieee.org/abstract/document/4781121/), Yifan Hu, Yehuda Koren, Chris Volinsky \[[pdf](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.167.5120&rep=rep1&type=pdf)\] 448 | * [Model-based biclustering of clickstream data](http://www.sciencedirect.com/science/article/pii/S0167947314002771) \[paywalled\], Volodymyr Melnykov 449 | * [Phase-functioned neural networks for character control](http://www.ipab.inf.ed.ac.uk/cgvu/phasefunction.pdf), Daniel Holden, Taku Komura, Jun Saito 450 | * [Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations](http://onlinelibrary.wiley.com/doi/10.1111/j.1467-9868.2008.00700.x/full), Håvard Rue, Sara Martino, Nicolas Chopin \[[pdf](http://people.ee.duke.edu/~lcarin/inla-rss.pdf)\] 451 | 452 | # 2017-04-26 453 | 454 | ## Chosen Paper 455 | \[paywalled\] [Statistical modelling of a terrorist network](http://onlinelibrary.wiley.com/doi/10.1111/rssa.12233/full), Murray Aitkin, 456 | Duy Vu, Brian Francis \[[slides](http://mathsofplanetearth.org.au/wp-content/uploads/2013/07/Aitkin-Murray.pdf)\] 457 | 458 | ## Other Suggestions 459 | * [Constraints versus priors](http://www.stat.berkeley.edu/~stark/Preprints/constraintsPriors14.pdf), Philip B. Stark 460 | * [To explain or to predict?](https://arxiv.org/abs/1101.0891), Galit Shmueli 461 | * [Collaborative filtering for implicit feedback datasets](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.167.5120&rep=rep1&type=pdf), Yifan Hu, Yehuda Koren, Chris Volinsky 462 | 463 | # 2017-04-12 464 | 465 | ## Chosen Paper 466 | [Deep Probabilistic Programming](https://arxiv.org/abs/1701.03757), Dustin Tran, Matthew D. Hoffman, Rif A. Saurous, Eugene Brevdo, Kevin Murphy, David M. Blei 467 | 468 | ## Other Suggestions 469 | * [Multi-talker Speech Separation and Tracing with Permutation Invariant Training of Deep Recurrent Neural Networks](https://arxiv.org/abs/1703.06284), Morten Kolbæk, Dong Yu, Zheng-Hua Tan, Jesper Jensen 470 | * [Constraints versus Priors](http://www.stat.berkeley.edu/~stark/Preprints/constraintsPriors14.pdf), Philip B. Stark 471 | * [Forecasting at Scale](https://facebookincubator.github.io/prophet/static/prophet_paper_20170113.pdf), Sean J. Taylor and Benjamin Letham 472 | * [Asymptotically exact inference in differentiable generative models](http://proceedings.mlr.press/v54/graham17a.html), Matthew Graham, Amos Storkey 473 | * [Judgment under Uncertainty: Heuristics and Biases](http://psiexp.ss.uci.edu/research/teaching/Tversky_Kahneman_1974.pdf), Amos Tversky, Daniel Kahneman 474 | 475 | # 2017-03-29 476 | 477 | ## Chosen Paper 478 | [Genotype–environment interactions in mouse behavior: A way out of the problem](https://www.researchgate.net/profile/Ilan_Golani/publication/7969318_Genotype-environment_interactions_in_mouse_behavior_A_way_out_of_the_problem/links/00b7d51d2cdac02d7f000000.pdf), Neri Kafkafi, Yoav Benjamini, Anat Sakov, Greg I. Elmer, and Ilan Golani 479 | 480 | ## Other Suggestions 481 | * [Universal adversarial perturbations](https://arxiv.org/abs/1610.08401), Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard 482 | * [Deep Voice: Real-time Neural Text-to-Speech](https://arxiv.org/abs/1702.07825), Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, Yongguo Kang, Xian Li, John Miller, Andrew Ng, Jonathan Raiman, Shubho Sengupta, Mohammad Shoeybi \[[blog post](http://research.baidu.com/deep-voice-production-quality-text-speech-system-constructed-entirely-deep-neural-networks/)\] 483 | * [Ambulance Location for Maximum Survival](https://sites.ualberta.ca/~aingolfs/documents/survival15november07.pdf), Erhan Erkut, Armann Ingolfsson, Güneş Erdoğan 484 | * [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://arxiv.org/abs/1603.05279), Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi 485 | 486 | # 2017-03-15 487 | 488 | ## Chosen Paper 489 | [Modeling Customer Lifetimes with Multiple Causes of Churn](http://people.stat.sfu.ca/~dac5/meetup1/churn.pdf), Michael Braun, David A. Schweidel 490 | 491 | ## Other Suggestions 492 | * [Deep Voice: Real-time Neural Text-to-Speech](https://arxiv.org/abs/1702.07825), Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, Yongguo Kang, Xian Li, John Miller, Andrew Ng, Jonathan Raiman, Shubho Sengupta, Mohammad Shoeybi \[[blog post](http://research.baidu.com/deep-voice-production-quality-text-speech-system-constructed-entirely-deep-neural-networks/)\] 493 | * [Asynchronous Methods for Deep Reinforcement Learning](https://arxiv.org/abs/1602.01783), Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu 494 | * [Is most published research really false?](http://biorxiv.org/content/early/2016/04/27/050575), Jeffrey T Leek, Leah R Jager 495 | * [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://arxiv.org/abs/1703.03864), Tim Salimans, Jonathan Ho, Xi Chen, Ilya Sutskever 496 | 497 | # 2017-03-01 498 | 499 | ## Chosen Paper 500 | [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://arxiv.org/abs/1701.08734), Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, Daan Wierstra 501 | 502 | ## Other Suggestions 503 | * [DeepCoder: Learning to Write Programs](https://arxiv.org/abs/1611.01989), Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow 504 | * [Negative training data can be harmful to text classification](http://dl.acm.org/citation.cfm?id=1870680), Xiao-Li Li, Bing Liu, See-Kiong Ng 505 | * [Forecasting at Scale](https://facebookincubator.github.io/prophet/static/prophet_paper_20170113.pdf), Sean J. Taylor and Benjamin Letham \[[blog post](https://research.fb.com/prophet-forecasting-at-scale/)\] 506 | 507 | # 2017-02-15 508 | 509 | ## Chosen Paper 510 | [Understanding deep learning requires rethinking generalization](https://arxiv.org/abs/1611.03530), Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals 511 | 512 | ## Other Suggestions 513 | * [Safe and Nested Endgame Solving for Imperfect-Information Games](https://www.cs.cmu.edu/~noamb/papers/17-AAAI-Refinement.pdf), Noam Brown, Tuomas Sandholm 514 | * [Automatic Differentiation Variational Inference](https://arxiv.org/abs/1603.00788), Alp Kucukelbir, Dustin Tran, Rajesh Ranganath, Andrew Gelman, David M. Blei 515 | * [Negative training data can be harmful to text classification](http://dl.acm.org/citation.cfm?id=1870680), Xiao-Li Li, Bing Liu, See-Kiong Ng 516 | 517 | # 2017-02-01 518 | 519 | ## Chosen Paper 520 | [Deep clustering: Discriminative embeddings for segmentation and separation](https://arxiv.org/abs/1508.04306), John R. Hershey, Zhuo Chen, Jonathan Le Roux, Shinji Watanabe 521 | 522 | ## Other Suggestions 523 | * [A Conceptual Introduction to Hamiltonian Monte Carlo](https://arxiv.org/abs/1701.02434), Michael Betancourt 524 | * [Latent Dirichlet Allocation](http://www.jmlr.org/papers/v3/blei03a.html), David M. Blei, Andrew Y. Ng, Michael I. Jordan 525 | * [On using expert opinion in ecological analyses: a frequentist approach](http://www.stat.ualberta.ca/~slele/publications/LeleAllen06.pdf), Subhash R. Lele, Kristie L. Allen 526 | * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://arxiv.org/abs/1502.03167), Sergey Ioffe, Christian Szegedy 527 | 528 | ## Bonus extra suggestion for LDA 529 | 530 | * [Finding scientific topics](http://www.pnas.org/content/101/suppl_1/5228.short), Thomas L. Griffiths, Mark Steyvers 531 | 532 | # 2017-01-18 533 | 534 | ## Chosen Paper 535 | [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://arxiv.org/abs/1701.01724), Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Michael Bowling 536 | 537 | ## Other Suggestions 538 | * [Unrolled Generative Adversarial Networks](https://arxiv.org/abs/1611.02163), Luke Metz, Ben Poole, David Pfau, Jascha Sohl-Dickstein 539 | * [Cluster failure: Why fMRI inferences for spatial extent have inflated false-positive rates](http://www.pnas.org/content/113/28/7900.full.pdf), Anders Eklunda, Thomas E. Nicholsd, and Hans Knutssona 540 | * [Beyond Object Recognition: Visual Sentiment Analysis with Deep Coupled Adjective and Noun Neural Networks](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/08/ijcai16.pdf), Jingwen Wang, Jianlong Fu, Yong Xu, Tao Mei 541 | * [Privacy-Preserving Data Analysis for the Federal Statistical Agencies](https://arxiv.org/abs/1701.00752), John Abowd, Lorenzo Alvisi, Cynthia Dwork, Sampath Kannan, Ashwin Machanavajjhala, Jerome Reiter 542 | 543 | # 2017-01-04 544 | 545 | ## Chosen Paper 546 | [Exploring Online Ad Images Using a Deep Convolutional Neural Network Approach](https://arxiv.org/abs/1509.00568), Michael Fire, Jonathan Schler 547 | 548 | ## Other Suggestions 549 | * [In-season prediction of batting averages: A field test of empirical Bayes and Bayes methodologies](https://arxiv.org/abs/0803.3697), Lawrence D. Brown 550 | * [Human-level concept learning through probabilistic program induction](http://web.mit.edu/cocosci/Papers/Science-2015-Lake-1332-8.pdf), Brenden M. Lake, Ruslan Salakhutdinov, Joshua B. Tenenbaum 551 | * [#HashtagWars: Learning a Sense of Humor](https://arxiv.org/abs/1612.03216), Peter Potash, Alexey Romanov, Anna Rumshisky 552 | 553 | # 2016-12-07 554 | 555 | ## Chosen Paper 556 | [Building Machines That Learn and Think Like People](https://arxiv.org/abs/1604.00289), Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman 557 | 558 | ## Other Suggestions 559 | * [A density-based algorithm for discovering clusters in large spatial databases with noise](https://webdocs.cs.ualberta.ca/~zaiane/courses/cmput695-00/papers/00153.pdf), M Ester, HP Kriegel, J Sander, X Xu 560 | * [Survival Analysis Part I: Basic concepts and first analyses](http://www.slaop.org/pdf/814Journ7.pdf), TG Clark, MJ Bradburn, SB Love and DG Altman 561 | * [Quantifying the evolution of individual scientific impact](http://www.dashunwang.com/pdf/Sinatra2016-Science.pdf), R Sinatra, D Wang, P Deville, C Song, A-L Barabási 562 | 563 | # 2016-11-23 564 | 565 | ## Chosen Paper 566 | [The Parable of Google Flu: Traps in Big Data Analysis](http://science.sciencemag.org/content/343/6176/1203), David Lazer, Ryan Kennedy, Gary King, Alessandro Vespignani 567 | 568 | ## Other Suggestions 569 | * [Hybrid computing using a neural network with dynamic external memory](http://www.nature.com/nature/journal/v538/n7626/abs/nature20101.html), Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann, Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield, Phil Blunsom, Koray Kavukcuoglu & Demis Hassabis 570 | * [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385), Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun 571 | * [Playing FPS Games with Deep Reinforcement Learning](https://arxiv.org/abs/1609.05521), Guillaume Lample, Devendra Singh Chaplot 572 | * [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://arxiv.org/abs/1611.04558), Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, Jeffrey Dean 573 | 574 | # 2016-11-09 575 | 576 | ## Chosen Paper 577 | [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](http://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks), Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun [\[code\]](https://github.com/smallcorgi/Faster-RCNN_TF) 578 | 579 | ## Other Suggestions 580 | * [Deep Gaussian Processes](http://www.jmlr.org/proceedings/papers/v31/damianou13a.pdf), Andreas C. Damianou, Neil D. Lawrence 581 | * [Stealing Machine Learning Models via Prediction APIs](https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/tramer), Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, Thomas Ristenpart [\[code\]](https://github.com/ftramer/Steal-ML) 582 | * [Distilling the Knowledge in a Neural Network](https://arxiv.org/abs/1503.02531), Geoffrey Hinton, Oriol Vinyals, Jeff Dean 583 | 584 | # 2016-10-26 585 | 586 | ## Chosen Paper 587 | [Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks](https://arxiv.org/abs/1602.03616), Anh Nguyen, Jason Yosinski, Jeff Clune [\[code\]](https://github.com/Evolving-AI-Lab/mfv) 588 | 589 | ## Other Suggestions 590 | * [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://arxiv.org/abs/1502.03167), Sergey Ioffe, Christian Szegedy 591 | * [Stealing Machine Learning Models via Prediction APIs](https://arxiv.org/abs/1609.02943), Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, Thomas Ristenpart 592 | * [Hybrid computing using a neural network with dynamic external memory](http://www.nature.com/articles/nature20101.epdf?author_access_token=ImTXBI8aWbYxYQ51Plys8NRgN0jAjWel9jnR3ZoTv0MggmpDmwljGswxVdeocYSurJ3hxupzWuRNeGvvXnoO8o4jTJcnAyhGuZzXJ1GEaD-Z7E6X_a9R-xqJ9TfJWBqz), Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann, Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield, Phil Blunsom, Koray Kavukcuoglu & Demis Hassabis 593 | * [Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables](https://arxiv.org/abs/1604.08880), Nils Y. Hammerla, Shane Halloran, Thomas Ploetz 594 | 595 | # 2016-10-12 596 | 597 | ## Chosen Paper 598 | [Origins of Presidential poll aggregation: A perspective from 2004 to 2012](https://web.math.princeton.edu/~sswang/wang15_IJF_origins-of-poll-aggregation.pdf), Samuel S.-H. Wang [\[code\]](http://election.princeton.edu/for-fellow-geeks/) 599 | 600 | ## Other Suggestions 601 | * [DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning](https://www.repository.cam.ac.uk/bitstream/handle/1810/250525/Lane,%20Georgiev,%20%26%20Qendro%202015%20UbiComp.pdf?sequence=1&isAllowed=y), Nicholas D. Lane, Petko Georgiev, Lorena Qendro 602 | * [Equality of Opportunity in Supervised Learning](https://drive.google.com/file/d/0B-wQVEjH9yuhanpyQjUwQS1JOTQ/view), Moritz Hardt, Eric Price, Nathan Srebro 603 | * [Dynamic Memory Networks for Visual and Textual Question Answering](https://arxiv.org/abs/1603.01417), Caiming Xiong, Stephen Merity, Richard Socher 604 | * [Detecting events and key actors in multi-person videos](https://arxiv.org/abs/1511.02917), Vignesh Ramanathan, Jonathan Huang, Sami Abu-El-Haija, Alexander Gorban, Kevin Murphy, Li Fei-Fei 605 | 606 | # 2015-11-25 607 | 608 | ## Chosen Paper 609 | [Parameter estimation for text analysis](http://www.arbylon.net/publications/text-est.pdf), Gregor Heinrich 610 | 611 | ## Other Suggestions 612 | * [Stan: A probabilistic programming language for Bayesian inference and optimization](http://www.stat.columbia.edu/~gelman/research/published/stan_jebs_2.pdf), Andrew Gelman, Daniel Lee, Jiqiang Guo 613 | * [No free lunch theorems for optimization](https://ti.arc.nasa.gov/m/profile/dhw/papers/78.pdf), David H. Wolpert, William G. Macready 614 | * [Towards a Mathematical Theory of Cortical Micro-circuits](http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1000532), Dileep George, Jeff Hawkins 615 | * [Expectation propagation as a way of life: A framework for Bayesian inference on partitioned data](https://arxiv.org/abs/1412.4869), Aki Vehtari, Andrew Gelman, Tuomas Sivula, Pasi Jylänki, Dustin Tran, Swupnil Sahai, Paul Blomstedt, John P. Cunningham, David Schiminovich, Christian Robert 616 | * [The Model Complexity Myth](https://jakevdp.github.io/blog/2015/07/06/model-complexity-myth/), Jake VanderPlas 617 | 618 | # 2016 Archives 619 | 620 | - 2016-10-12: [Gaussian processes for time-series modelling](http://rsta.royalsocietypublishing.org/content/371/1984/20110550.short), S. Roberts, M. Osborne, M. Ebden, S. Reece, N. Gibson, S. Aigrain \[[pdf](https://pdfs.semanticscholar.org/4c0c/f51fdcbb1da12f3c7e24479612fc15b9c1d3.pdf)\] 621 | - 2016-09-28: [Boltzmann Machines](http://people.stat.sfu.ca/~dac5/BoltzmannMachines.pdf), Geoffrey Hinton 622 | - 2016-09-14: [XGBoost: A Scalable Tree Boosting System](https://arxiv.org/abs/1603.02754), Tianqi Chen, Carlos Guestrin 623 | - 2016-08-31: [Visualizing Data using t-SNE](http://www.cs.toronto.edu/~hinton/absps/tsne.pdf), Laurens van der Maaten, Geoffrey Hinton 624 | - 2016-08-17: [Big Learning with Bayesian Methods](https://arxiv.org/abs/1411.6370 ), Jun Zhu, Jianfei Chen, Wenbo Hu 625 | - 2016-08-03: [Abandoning Objectives: Evolution through the Search for Novelty Alone](http://eplex.cs.ucf.edu/papers/lehman_ecj11.pdf), Joel Lehman, Kenneth O. Stanley 626 | - 2016-07-20: [POINTWISE: Predicting Points and Valuing Decisions in Real Time with NBA Optical Tracking Data](http://www.lukebornn.com/papers/cervone_ssac_2014.pdf), Dan Cervone, Alexander D’Amour, Luke Bornn, Kirk Goldsberry 627 | - 2016-07-06: [Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records](http://www.nature.com/articles/srep26094), Riccardo Miotto, Li Li, Brian A. Kidd & Joel T. Dudley 628 | - 2016-06-22: [Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation](https://arxiv.org/pdf/1406.1078v3.pdf), Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio 629 | - 2016-06-08: [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/abs/1511.06434), Alec Radford, Luke Metz, Soumith Chintala 630 | - 2016-05-25: [Intriguing properties of neural networks](https://arxiv.org/pdf/1312.6199v4.pdf), Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus 631 | - 2016-05-11: [“Why Should I Trust You?” Explaining the Predictions of Any Classifier](https://arxiv.org/pdf/1602.04938v1.pdf), Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin 632 | - 2016-04-27: [Linear Models: A Useful “Microscope” for Causal Analysis](http://ftp.cs.ucla.edu/pub/stat_ser/r409.pdf), Judea Pearl 633 | - 2016-04-13: [INFERRING CAUSAL IMPACT USING BAYESIAN STRUCTURAL TIME-SERIES MODELS](http://de.arxiv.org/pdf/1506.00356), Kay H. Brodersen, Fabian Gallusser, Jim Koehler, Nicolas Remy and Steven L. Scott 634 | - 2016-03-30: [Mastering the game of Go with deep neural networks and tree search](http://www.willamette.edu/~levenick/cs448/goNature.pdf), David Silver, Aja Huang1, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche,Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu1, Thore Graepel1, Demis Hassabis 635 | - 2016-03-16: [A Neural Algorithm of Artistic Style](https://arxiv.org/pdf/1508.06576v2.pdf), Leon A. Gatys, Alexander S. Ecker, Matthias Bethge 636 | - 2016-03-02: [Probabilistic Methods for Time-Series Analysis](http://www.lancs.ac.uk/~killick/Pub/EckleyFearnheadKillick2010.pdf), Idris A. Eckley, Paul Fearnhead, Rebecca Killick 637 | - 2016-02-17: [Practical recommendations for gradient-based training of deep architectures](https://arxiv.org/abs/1206.5533), Yoshua Bengio 638 | - 2016-01-20: [Expectation propagation as a way of life](https://arxiv.org/pdf/1412.4869v1.pdf), Andrew Gelman, Aki Vehtari, Pasi Jylänki, Christian Robert, Nicolas Chopink, John P. Cunningham 639 | - 2016-01-06: [ 640 | Aggregation for the probabilistic traveling salesman problem](http://www.sciencedirect.com/science/article/pii/S0305054805000808), Ann Melissa Campbell 641 | --------------------------------------------------------------------------------