Week Ending 11.17.19
RESEARCH WATCH: 11.17.19
Over the past week, 883 new papers were published in "Computer Science".
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 20 times, including in the article DeepMind AI Beats Human Historians at Deciphering Ancient Texts in History News Network. The paper author, Yannis Assael (DeepMind), was quoted saying "It’s all about how we can help the experts".
Leading researcher Kyunghyun Cho (New York University) published "Dont Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training", which has 0 shares on Twitter so far. The investigators show how all of these problems can be addressed by extending the recently introduced unlikelihood loss (Welleck et al., 2019) to these cases.
Over the past week, 75 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 IBM: "Evading Real-Time Person Detectors by Adversarial T-shirt" by Kaidi Xu et al (Oct 2019), which was referenced 10 times, including in the article This T-shirt could make you invisible to deep neural networks in News @ Northeastern. The paper author, Shelley Lin, was quoted saying "We had to model the transformation of the shirt while people walk, and use that in our calculations".
Leading researcher Aaron Courville (Université de Montréal) came out with "Selective Brain Damage: Measuring the Disparate Impact of Model Pruning".
Over the past week, 139 new papers were published in "Computer Science - Computer Vision and Pattern Recognition".
The paper discussed most in the news over the past week was by a team at IBM: "Evading Real-Time Person Detectors by Adversarial T-shirt" by Kaidi Xu et al (Oct 2019)
Leading researcher Aaron Courville (Université de Montréal)
Over the past week, 22 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)
Over the past week, 22 new papers were published in "Computer Science - Human-Computer Interaction".
The paper discussed most in the news over the past week was by a team at University of Bristol: "Reach Out and Help: Assisted Remote Collaboration through a Handheld Robot" by Janis Stolzenwald et al (Oct 2019), which was referenced 4 times, including in the article Robot overlords? More like co-verlords. The future is human robot collaboration in Digital Trends. The paper author, Janis Stolzenwald (University of Bristol), was quoted saying "We see applications in maintenance, inspection and manufacturing".
This week was very active for "Computer Science - Learning", with 366 new papers.
The paper discussed most in the news over the past week was by a team at Lawrence Berkeley National Laboratory: "Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEs" by Liu Yang et al (Oct 2019), which was referenced 11 times, including in the article Leveraging Exaflops Performance to Remediate Nuclear Waste in HPC Wire. The paper author, Alex Tartakovsky, was quoted saying "Estimating the Hanford Site properties from data only would require more than a million measurements, and in practice we have maybe a thousand. The laws of physics help us compensate for the lack of data."
Leading researcher Aaron Courville (Université de Montréal)
Over the past week, 17 new papers were published in "Computer Science - Multiagent Systems".
Over the past week, 16 new papers were published in "Computer Science - Neural and Evolutionary Computing".
This week was active for "Computer Science - Robotics", with 48 new papers.
The paper discussed most in the news over the past week was by a team at University of Bristol: "Reach Out and Help: Assisted Remote Collaboration through a Handheld Robot" by Janis Stolzenwald et al (Oct 2019)