This page shows the most relevant public items for Machine Learning, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Jul 25, 2017 • arxiv.org • Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin
The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on con...
Paper • Apr 17, 2017 • arxiv.org • Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions ...
Paper • Mar 17, 2016 • arxiv.org • Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio
We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for c...
Paper • May 3, 2016 • arxiv.org • Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A. Horowitz, William J. Dally
State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with lim...
Paper • Nov 4, 2016 • arxiv.org • Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer
Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that ac...
Paper • Dec 29, 2016 • arxiv.org • Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg
We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over diff...
Paper • Dec 16, 2018 • arxiv.org • Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros
Realistic image manipulation is challenging because it requires modifying the image appearance in a user-controlled way, while preserving the realism of the result. Unless the user has considerable...
Paper • Oct 5, 2016 • arxiv.org • Richard Zhang, Phillip Isola, Alexei A. Efros
Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches ...
Paper • Sep 19, 2016 • arxiv.org • Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, Koray Kavukcuoglu
This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample ...
Paper • Jun 14, 2016 • arxiv.org • Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Nando de Freitas
The move from hand-designed features to learned features in machine learning has been wildly successful. In spite of this, optimization algorithms are still designed by hand. In this paper we show ...
Paper • Jul 21, 2016 • arxiv.org • Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton
Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique call...
Paper • Dec 19, 2013 • arxiv.org • Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural networ...
Paper • Jul 5, 2019 • arxiv.org • Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can op...
Paper • Jan 27, 2016 • www.nature.com • David Silver, Aja Huang, 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 Kavukcuoglu, Thore Graepel, Demis Hassabis
A computer Go program based on deep neural networks defeats a human professional player to achieve one of the grand challenges of artificial intelligence.
Paper • Dec 8, 2015 • arxiv.org • Hado van Hasselt, Arthur Guez, David Silver
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they har...
Paper • Aug 28, 2016 • arxiv.org • Sergey Levine, Peter Pastor, Alex Krizhevsky, Deirdre Quillen
We describe a learning-based approach to hand-eye coordination for robotic grasping from monocular images. To learn hand-eye coordination for grasping, we trained a large convolutional neural netwo...
Paper • Mar 22, 2013 • arxiv.org • Alex Graves, Abdel-rahman Mohamed, Geoffrey Hinton
Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labe...
Paper • Dec 8, 2015 • arxiv.org • Dario Amodei, Rishita Anubhai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Adam Coates, Greg Diamos, Erich Elsen, Jesse Engel, Linxi Fan, Christopher Fougner, Tony Han, Awni Hannun, Billy Jun, Patrick LeGresley, Libby Lin, Sharan Narang, Andrew Ng, Sherjil Ozair, Ryan Prenger, Jonathan Raiman, Sanjeev Satheesh, David Seetapun, Shubho Sengupta, Yi Wang, Zhiqian Wang, Chong Wang, Bo Xiao, Dani Yogatama, Jun Zhan, Zhenyao Zhu
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-en...
Paper • Mar 14, 2016 • arxiv.org • Dzmitry Bahdanau, Jan Chorowski, Dmitriy Serdyuk, Philemon Brakel, Yoshua Bengio
Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain sep...
Paper • Jun 5, 2014 • arxiv.org • Alex Graves
This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approac...
It ranks public content for Machine Learning using recent discussion, review, and engagement signals so you can triage faster. This guidance is specific to Machine Learning topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use weekly for fast-moving updates, monthly for stable trend confirmation, and all-time for evergreen references. This guidance is specific to Machine Learning topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use the linked entities section to jump to labs, companies, and experts connected to this topic and explore their timelines. This guidance is specific to Machine Learning topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Yes. Use the follow button on this page to subscribe and track new high-signal activity. This guidance is specific to Machine Learning topic page on Attendemia and is written so it still makes sense without reading other sections on the page.