Week Ending 7.19.2020
RESEARCH WATCH: 7.19.2020
Over the past week, 84 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 DeepMind: "Acme: A Research Framework for Distributed Reinforcement Learning" by Matt Hoffman et al (Jun 2020), which was referenced 5 times, including in the article Best of arXiv.org for AI, Machine Learning, and Deep Learning – June 2020 in InsideBIGDATA. The paper got social media traction with 174 shares. A user, @dennybritz, tweeted "This new RL framework looks pretty cool. There seem to be quite a few abstractions you need to learn about, but the effort may be worth it if you want to scale up your agents. The tutorial on arXiv is excellent".
Leading researcher Oriol Vinyals (DeepMind) came out with "AlignNet: Unsupervised Entity Alignment".
The paper shared the most on social media this week is by a team at University College London: "Learning Reasoning Strategies in End-to-End Differentiable Proving" by Pasquale Minervini et al (Jul 2020) with 88 shares. @popular_ML (Popular ML resources) tweeted "The most popular ArXiv tweet in the last 24h".
The most influential Twitter user discussing papers is EMZOTIC who shared "Projectile Trajectory of Penguins Faeces and Rectal Pressure Revisited" by Hiroyuki Tajima et al (Jul 2020) and said: "The physics of pooping penguins. You’re welcome 🐧 💩".
This week was very active for "Computer Science - Computer Vision and Pattern Recognition", with 358 new papers.
The paper discussed most in the news over the past week was by a team at INRIA: "End-to-End Object Detection with Transformers" by Nicolas Carion et al (May 2020), which was referenced 7 times, including in the article Transformers for Vision/DETR in Swlh - Medium. The paper also got the most social media traction with 639 shares. A Twitter user, @theairbend3r, said "End-to-End Object Detection with Transformers by Facebook AI DETR uses a conventional CNN backbone to learn a 2D representation of an input image. #deeplearning #machinelearning #PyTorch #research", while @KrAbhinavGupta posted "Very interesting".
Leading researcher Oriol Vinyals (DeepMind) came out with "AlignNet: Unsupervised Entity Alignment".
The paper shared the most on social media this week is "Accelerating 3D Deep Learning with PyTorch3D" by Nikhila Ravi et al (Jul 2020) with 170 shares. @drsxr (Stephen Borstelmann MD) tweeted "Differentiable machine learning is 100% the way to go".
The most influential Twitter user discussing papers is EMZOTIC who shared "Projectile Trajectory of Penguins Faeces and Rectal Pressure Revisited" by Hiroyuki Tajima et al (Jul 2020)
This week was active for "Computer Science - Computers and Society", with 43 new papers.
The paper discussed most in the news over the past week was "Senior Living Communities: Made Safer by AI" by Ashutosh Saxena et al (Jul 2020), which was referenced 18 times, including in the article Senior Living Communities: Made Safer by AI in PR Newswire.
The paper shared the most on social media this week is by a team at Google: "Bringing the People Back In: Contesting Benchmark Machine Learning Datasets" by Emily Denton et al (Jul 2020) with 65 shares. @math_rachel (Rachel Thomas) tweeted "Datasets (particularly benchmarks) are infrastructure: a foundation for other tools & tech, tending to seep into the background, shaped by specific aims, seeming natural from one perspective but jarring from another".
The most influential Twitter user discussing papers is EMZOTIC who shared "Projectile Trajectory of Penguins Faeces and Rectal Pressure Revisited" by Hiroyuki Tajima et al (Jul 2020)
Over the past week, 21 new papers were published in "Computer Science - Human-Computer Interaction".
This week was extremely active for "Computer Science - Learning", with 485 new papers.
The paper discussed most in the news over the past week was by a team at DeepMind: "Acme: A Research Framework for Distributed Reinforcement Learning" by Matt Hoffman et al (Jun 2020)
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Revisiting Fundamentals of Experience Replay" @rupspace tweeted "This is a very nice paper!".
The paper shared the most on social media this week is "Unsupervised machine learning via transfer learning and k-means clustering to classify materials image data" by Ryan Cohn (Department of Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, PA, USA) et al (Jul 2020) with 172 shares. The investigators demonstrate how to construct, use, and evaluate a high performance unsupervised machine learning system for classifying images in a popular microstructural dataset.
The most influential Twitter user discussing papers is EMZOTIC who shared "Projectile Trajectory of Penguins Faeces and Rectal Pressure Revisited" by Hiroyuki Tajima et al (Jul 2020)
Over the past week, 14 new papers were published in "Computer Science - Multiagent Systems".
The paper discussed most in the news over the past week was "Simulating COVID-19 in a University Environment" by Philip T. Gressman et al (Jun 2020), which was referenced 99 times, including in the article 5 Bigger and Better Ideas for Fall 2020 in Inside Higher Ed. The paper author, Jennifer Peck, was quoted saying "What we’ve shown is that if the social side is under control, you can manage the spread through academic contacts. So having said that, can you get the social side of the contacts under control? At this point, that’s a first-order question". The paper also got the most social media traction with 156 shares. On Twitter, @DCBPhDV2 observed "Y'all. "In the absence of any intervention, all scenarios end with effectively all susceptible community members developing #COVID19 by the end of the semester, with peak infection rates reached between 20 and 40 days into the semester." #HigherEd".
Over the past week, 19 new papers were published in "Computer Science - Neural and Evolutionary Computing".
The paper discussed most in the news over the past week was "An Astrocyte-Modulated Neuromorphic Central Pattern Generator for Hexapod Robot Locomotion on Intels Loihi" by Ioannis Polykretis et al (Jun 2020), which was referenced 2 times, including in the article Researchers Successfully Recreate Astrocyte Cell Function in a Hexapod Robot in Interesting Engineering. The paper author, Konstantinos Michmizos, was quoted saying "Everything that artificial neural nets do, and they do a lot these days, is based on the neurocomputing dogma that 'brain equals neurons. Astrocytes are two to 10 times more plentiful than neurons . The impact of understanding or mimicking what more of half the brain is doing is enormous." The paper got social media traction with 9 shares. The researchers propose a brain - morphic CPG controler based on a comprehensive spiking neural - astrocytic network that generates two gait patterns for a hexapod robot. A user, @Olumide_jfST, tweeted "Seeing this is so satisfying 😭Neuro peeps who know me personally KNOW I’ve always wondered why astrocytes haven’t been included in typical paradigms for modeling network activity. Perhaps it begs the question, will they ever be included in CONVNETS? 🤔".
The paper shared the most on social media this week is by a team at University College London: "Learning Reasoning Strategies in End-to-End Differentiable Proving" by Pasquale Minervini et al (Jul 2020)
The most influential Twitter user discussing papers is EMZOTIC who shared "Projectile Trajectory of Penguins Faeces and Rectal Pressure Revisited" by Hiroyuki Tajima et al (Jul 2020)
This week was active for "Computer Science - Robotics", with 52 new papers.
The paper discussed most in the news over the past week was by a team at Carnegie Mellon University: "Multi-modal Transfer Learning for Grasping Transparent and Specular Objects" by Thomas Weng et al (May 2020), which was referenced 9 times, including in the article Transparent, reflective objects now within grasp of robots in EurekAlert!. The paper was shared 4 times in social media.
The paper shared the most on social media this week is "Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators" by Yasuhiro Fujita et al (Jul 2020) with 63 shares. @hillbig (Daisuke Okanohara) tweeted "Work by our PFN RL team. A grasping system using a mobile manipulator (HSR) with a wrist camera (no fixed camera), trained by distributed RL in a simulated environment. Learn active vision behavior (search for the object actively)".
The most influential Twitter user discussing papers is EMZOTIC who shared "Projectile Trajectory of Penguins Faeces and Rectal Pressure Revisited" by Hiroyuki Tajima et al (Jul 2020)