Week Ending 10.27.19
RESEARCH WATCH: 10.27.19
Over the past week, 1,024 new papers were published in "Computer Science".
The paper discussed most in the news over the past week was by a team at Google: "Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules" by Benjamin Sanchez-Lengeling et al (Oct 2019), which was referenced 18 times, including in the article Google is training graph neural networks to predict smells in Venturebeat. The paper author, Alexander B Wiltschko, was quoted saying "We know we have chiral pairs in our data set, and we know we cannot possibly be predicting them correctly".
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery", which has 0 shares on Twitter so far.
Over the past week, 69 new papers were published in "Computer Science - Artificial Intelligence".
The paper discussed most in the news over the past week was by a team at OpenAI: "Solving Rubiks Cube with a Robot Hand" by OpenAI et al (Oct 2019), which was referenced 7 times, including in the article Why a robot that can ‘solve’ Rubik’s Cube one-handed has the AI community at war in The Next Web.
Leading researcher Kyunghyun Cho (New York University) published "Capacity, Bandwidth, and Compositionality in Emergent Language Learning".
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 238 new papers.
The paper discussed most in the news over the past week was by a team at Massachusetts Institute of Technology: "Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video" by Maria Bauza et al (Oct 2019), which was referenced 14 times, including in the article Pushy robots learn the fundamentals of object manipulation in TechRistic. The paper author, Rodriguez, was quoted saying "Imagine pushing a table with four legs, where most weight is over one of the legs. When you push the table, you see that it rotates on the heavy leg and have to readjust. Understanding that mass distribution, and its effect on the outcome of a push, is something robots can learn with this set of objects".
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery".
Over the past week, 21 new papers were published in "Computer Science - Computers and Society".
The paper discussed most in the news over the past week was "Restoring ancient text using deep learning: a case study on Greek epigraphy" by Yannis Assael et al (Oct 2019), which was referenced 17 times, including in the article Deep learning enlightens scholars puzzling over ancient texts in Tech Xplore. The paper author, Yannis Assael (DeepMind), was quoted saying "It’s all about how we can help the experts".
This week was active for "Computer Science - Human-Computer Interaction", with 25 new papers.
This week was very active for "Computer Science - Learning", with 425 new papers.
The paper discussed most in the news over the past week was by a team at Google: "Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules" by Benjamin Sanchez-Lengeling et al (Oct 2019)
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Predicting ice flow using machine learning".
Over the past week, 18 new papers were published in "Computer Science - Multiagent Systems".
The paper discussed most in the news over the past week was by a team at The Hebrew University of Jerusalem: "Hijacking Routes in Payment Channel Networks: A Predictability Tradeoff" by Saar Tochner et al (Sep 2019), which was referenced 9 times, including in the article Researchers Uncover Bitcoin ‘Attack’ That Could Slow or Stop Lightning Payments in BusinessMayor.com. The paper also got the most social media traction with 118 shares. A user, @c4chaos, tweeted "wait. wut? you mean #Lightning can make #Bitcoin less decentralized than $EOS? 🤷🏻♂️⚡️ “We find that in the current network nearly 60% of all routes pass through only five nodes, while 80% go through only 10 nodes.“ see".
Leading researcher Kyunghyun Cho (New York University) came out with "Capacity, Bandwidth, and Compositionality in Emergent Language Learning".
Over the past week, 24 new papers were published in "Computer Science - Neural and Evolutionary Computing".
The paper discussed most in the news over the past week was by a team at DeepMind: "Meta-Learning Deep Energy-Based Memory Models" by Sergey Bartunov et al (Oct 2019), which was referenced 2 times, including in the article What Are Deep Energy-Based Memory Models? in Analytics India Magazine.
This week was active for "Computer Science - Robotics", with 62 new papers.
The paper discussed most in the news over the past week was by a team at Massachusetts Institute of Technology: "Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video" by Maria Bauza et al (Oct 2019)
Leading researcher Sergey Levine (University of California, Berkeley) published "Contextual Imagined Goals for Self-Supervised Robotic Learning".