Pulkit Agrawal    @pulkitology
Earlier in the year we taught a virtual, but hands-on course on sensorimotor learning spanning RL, imitation, exploration, model learning, self-supervision, robot learning and related topics. In case you are interested, here is the material https://t.co/ftoeEge9ni @taochenshh #AI
 Reply      Retweet   20      Like    105   





Lex Fridman    @lexfridman
Here's my conversation with Ishan Misra (@imisra_), research scientist at FAIR, working on self-supervised visual learning: getting machines to understand images & video with little help from humans. This is one of the most exciting topics in AI today. https://t.co/iOFVG8l7WG
 Reply      Retweet   49      Like    523   

Tennis Channel    @TennisChannel
"Without pressure there is no professional sport. If you are aiming to be at the top of the game you better start learning how to deal with pressure." @DjokerNole spoke on being able to cope with those tougher moments, and learning more with time. https://t.co/vis7ueiGVt

David Pfau    @pfau
For those who, like myself, enjoy importing esoteric ideas from differential geometry to machine learning: a foliated theory of transfer learning https://t.co/CL1Y75s56W

Yann LeCun    @ylecun
2 more lectures from the Spring'21 NYU Deep Learning course. Energy-Based Model, a general framework to describe most ML/stat methods, whether probabilistic or not, supervised, weakly sup, self-sup, or unsup, contrastive or not, with latent variables or not, generative or not.



 







Andrew Gordon Wilson

Simone Scardapane

Wojciech Czarnecki

Petar Veličković

Efstratios Gavves

Andrew Glassner