Week Ending 12.02.18
RESEARCH WATCH: 12.02.18
Over the past week, 224 new papers were published in "Computer Science".
The paper discussed most in the news over the past week was "Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects" by Michael A. Alcorn et al (Nov 2018), which was referenced 3 times, including in the article Google's image recognition AI fooled by new tricks in ZDNet.
Leading researcher Aaron Courville (Université de Montréal) published "Systematic Generalization: What Is Required and Can It Be Learned?".
Over the past week, 89 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 University of Edinburgh: "Exploration by Random Network Distillation" by Yuri Burda et al (Oct 2018), which was referenced 2 times, including in the article Curiosity in Deep Reinforcement Learning in Medium.com.
Leading researcher Aaron Courville (Université de Montréal) came out with "Systematic Generalization: What Is Required and Can It Be Learned?".
This week was active for "Computer Science - Computer Vision and Pattern Recognition", with 259 new papers.
The paper discussed most in the news over the past week was "Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects" by Michael A. Alcorn et al (Nov 2018), which was referenced 3 times, including in the article Google's image recognition AI fooled by new tricks in ZDNet.
Leading researcher Luc Van Gool (Computer Vision Laboratory) published "Practical Full Resolution Learned Lossless Image Compression".
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 "AI Fairness for People with Disabilities: Point of View" by Shari Trewin (Nov 2018), which was referenced 1 time, including in the article Can you make an AI that isn’t ableist? in Technology Review.
Over the past week, 179 new papers were published in "Computer Science - Learning".
The paper discussed most in the news over the past week was "Time Series Classification to Improve Poultry Welfare" by Alireza Abdoli et al (Nov 2018), which was referenced 16 times, including in the article A Fitbit for chickens? Sounds silly, but it could revolutionize poultry farms in Digital Trends. The paper author, Amy Murillo, was quoted saying "We are interested in studying chicken behaviors, but traditional behavior studies required the researchers to make in-person observations or watch hours of video".
Leading researcher Chris Dyer (DeepMind) came out with "Sentence Encoding with Tree-constrained Relation Networks".
Over the past week, 32 new papers were published in "Computer Science - Robotics".
The paper discussed most in the news over the past week was "AutOTranS: an Autonomous Open World Transportation System" by Brayan S. Zapata-Impata et al (Oct 2018), which was referenced 2 times, including in the article Video Friday: InSight Mars Lander, and More in Spectrum Online.
Leading researcher Sergey Levine (University of California, Berkeley) published "Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play".