Eye On AI

View Original

Week Ending 4.11.2021

RESEARCH WATCH: 4.11.2021

This week was active for "Computer Science", with 1,170 new papers.

This week was very active for "Computer Science - Artificial Intelligence", with 173 new papers.

  • The paper discussed most in the news over the past week was by a team at Université de Montréal: "Towards Causal Representation Learning" by Bernhard Schölkopf et al (Feb 2021), which was referenced 9 times, including in the article Why machine learning struggles with causality in KDNuggets. The paper got social media traction with 467 shares. A Twitter user, @NalKalchbrenner, posted "Causality in ML is one of those slippery concepts that are hard to get a good grip on - a bit like the concepts of consciousness and perhaps truth. This paper makes an attempt 👇", while @YisongMiao posted "Haven't read, seems like very interesting! RT for self-arxiv. Thanks!".

  • Leading researcher Pieter Abbeel (University of California, Berkeley) published "GEM: Group Enhanced Model for Learning Dynamical Control Systems" The authors take advantage of these structures to build effective dynamical models that are amenable to sample - based learning.

  • The paper shared the most on social media this week is by a team at MIT Computer Science and Artificial Intelligence Laboratory: "AST: Audio Spectrogram Transformer" by Yuan Gong et al (Apr 2021) with 95 shares. @yieldthought (Mark) tweeted "10. I should have read concurrent work mentioned above more closely ( Many differences: patch overlap (we have none), ImageNet pretrain (we don’t) embeddings (we learn), distillation (we do). Joint ablation would be fun!".

This week was very active for "Computer Science - Computer Vision and Pattern Recognition", with 348 new papers.

This week was active for "Computer Science - Computers and Society", with 32 new papers.

This week was active for "Computer Science - Human-Computer Interaction", with 34 new papers.

This week was very active for "Computer Science - Learning", with 383 new papers.

Over the past week, 14 new papers were published in "Computer Science - Multiagent Systems".

  • The paper shared the most on social media this week is "Scaling Scaling Laws with Board Games" by Andrew L. Jones (Apr 2021) with 104 shares. @Inoryy (Roman Ring) tweeted "Scaling Laws seem to be even more generally applicable! I've seen this work unfold from a simple idea to a great paper it is today. It stands on its own merit but doubly so as Andy did it all as an independent researcher!".

Over the past week, 17 new papers were published in "Computer Science - Neural and Evolutionary Computing".

This week was very active for "Computer Science - Robotics", with 72 new papers.


EYE ON A.I. GETS READERS UP TO DATE ON THE LATEST FUNDING NEWS AND RELATED ISSUES. SUBSCRIBE FOR THE WEEKLY NEWSLETTER.