1
Deformable Convolutional Networks
Source ↗Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei
Mar 22, 2017·9895 checkouts·arxiv.org
Best Machine Learning Papers for 2017
The highest-signal papers on Machine Learning, ranked by community reviews and momentum.
Canonical intent: topic=machine-learning|type=paper|year=2017
Top Picks
2
3
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
Source ↗Sergey Ioffe
Mar 30, 2017·9737 checkouts·arxiv.org
4
5
Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets
Source ↗Rotem Dror, Gili Baumer, Marina Bogomolov, Roi Reichart
Sep 27, 2017·9398 checkouts·arxiv.org
6
Least Squares Generative Adversarial Networks
Source ↗Xudong Mao, Qing Li, Haoran Xie, Raymond Y. K. Lau, Zhen Wang
Feb 24, 2017·9292 checkouts·arxiv.org
7
Convolutional Sequence to Sequence Learning
Source ↗Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin
Jul 25, 2017·9257 checkouts·arxiv.org
8
Deep Voice: Real-time Neural Text-to-Speech
Source ↗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
Mar 7, 2017·9257 checkouts·arxiv.org
9
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Source ↗Tim Salimans, Jonathan Ho, Xi Chen, Ilya Sutskever
Mar 10, 2017·8582 checkouts·arxiv.org
10
Enriching Word Vectors with Subword Information
Source ↗Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov
Jun 19, 2017·8166 checkouts·arxiv.org
11
LSTM: A Search Space Odyssey
Source ↗Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, Jürgen Schmidhuber
Oct 4, 2017·8092 checkouts·arxiv.org
12
Very Deep Convolutional Networks for Text Classification
Source ↗Alexis Conneau, Holger Schwenk, Loïc Barrault, Yann Lecun
Jan 27, 2017·7959 checkouts·arxiv.org
13
PixelNet: Representation of the pixels, by the pixels, and for the pixels
Source ↗Aayush Bansal, Xinlei Chen, Bryan Russell, Abhinav Gupta, Deva Ramanan
Feb 21, 2017·7787 checkouts·arxiv.org
14
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
Source ↗Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jungkwon Lee, Jiwon Kim
Mar 15, 2017·7599 checkouts·arxiv.org
15
Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
Source ↗Graham Neubig
Mar 5, 2017·7524 checkouts·arxiv.org
16
Tacotron: Towards End-to-End Speech Synthesis
Source ↗Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, Quoc Le, Yannis Agiomyrgiannakis, Rob Clark, Rif A. Saurous
Apr 6, 2017·7302 checkouts·arxiv.org
17
Advances in Pre-Training Distributed Word Representations
Source ↗Tomas Mikolov, Edouard Grave, Piotr Bojanowski, Christian Puhrsch, Armand Joulin
Dec 26, 2017·7267 checkouts·arxiv.org
18
Fast and Accurate Entity Recognition with Iterated Dilated Convolutions
Source ↗Emma Strubell, Patrick Verga, David Belanger, Andrew McCallum
Jul 22, 2017·6995 checkouts·arxiv.org
19
Understanding deep learning requires rethinking generalization
Source ↗Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals
Feb 26, 2017·6866 checkouts·arxiv.org
20
Adam: A Method for Stochastic Optimization
Source ↗Diederik P. Kingma, Jimmy Ba
Jan 30, 2017·6721 checkouts·arxiv.org
21
Dermatologist-level classification of skin cancer with deep neural networks - Nature
Source ↗Andre Esteva, Brett Kuprel, Roberto A. Novoa, Justin Ko, Susan M. Swetter, Helen M. Blau, Sebastian Thrun
Jan 25, 2017·6607 checkouts·nature.com
22
Deep Photo Style Transfer
Source ↗Fujun Luan, Sylvain Paris, Eli Shechtman, Kavita Bala
Mar 22, 2017·6267 checkouts·arxiv.org
23
Adaptive Computation Time for Recurrent Neural Networks
Source ↗Alex Graves
Feb 21, 2017·5844 checkouts·arxiv.org
24
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Source ↗Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam
Apr 17, 2017·5716 checkouts·arxiv.org
25
26
A Simple but Tough-to-Beat Baseline for Sentence Embeddings
Source ↗Sanjeev Arora, Yingyu Liang, Tengyu Ma
Feb 6, 2017·5083 checkouts·openreview.net
27
Attention Is All You Need
Source ↗Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
Jun 12, 2017·171 checkouts·arxiv.org
FAQ
How is this “best Machine Learning Papers” collection ranked?
This page ranks Machine Learning Papers using topic relevance, checkout momentum, source diversity, and freshness signals. Rankings are recalculated as new items and engagement arrive, so readers see resources that are both high quality and currently useful for implementation, research, and practical decision making. Canonical intent key: topic=machine-learning|type=paper|year=2017.
How do you prevent duplicate collection pages?
Attendemia maps each slug variant, including best-of and year forms, to one canonical intent key. If two URLs describe the same topic, type, and timeframe, non-canonical versions permanently redirect. This consolidates crawl signals, avoids duplicate content dilution, and helps search engines index the strongest single page.
When does a year page stay separate from evergreen?
A year-specific page stays separate only when its item set is materially different from evergreen and has enough ranking depth. When overlap is high, the year URL redirects to the evergreen canonical page. This avoids thin duplication while preserving genuinely distinct annual collections for search users.
Are these paid recommendations?
No. These recommendations are not paid placements. Attendemia ranks items from public metadata, source quality coverage, and user engagement signals, then orders them by practical usefulness. Sponsorship does not buy rank position, so this page should be interpreted as editorial curation rather than advertising inventory.