Tweet  

Tengyu Ma    @tengyuma   ·   10/13/2021
Thinking of applying self-supervised learning (SSL) on your uncurated, imbalanced datasets? Good news: we found SSL is more robust to long tails than supervised representations. We also present theoretical and empirical analyses and an improved algorithm. https://t.co/VuZzklRzRw
 
 Reply      Retweet   85      Like     413    

More by:   Tengyu Ma
zoom in  
 








  More Tweets  

Yann LeCun    @ylecun   ·   6/29/2021
A thread on self-supervised learning, with links.
 Reply      Retweet   63      Like     290    

More by:   Yann LeCun
zoom in  
 



DeepMind    @DeepMind   ·   6/16/2020
Moving away from negative pairs in self-supervised representation learning: our new SotA method, Bootstrap Your Own Latent (BYOL), narrows the gap between self-supervised & supervised methods simply by predicting previous versions of itself. See here: https://t.co/qyaSXnPQjN
 
 Reply      Retweet   238      Like     837    

More by:   DeepMind
zoom in  
 



Sergey Levine    @svlevine   ·   10/11/2021
In robotic learning, we start from scratch for every experiment, with custom per-task data. Generalization is poor, because the dataset is narrow. In supervised learning domains, there are large reusable datasets (e.g., ImageNet, MS-COCO). What would be "ImageNet" in robotics?
 
 Reply      Retweet   1      Like     2    

More by:   Sergey Levine
zoom in  
 



Sebastian Raschka    @rasbt   ·   9/25/2021
There is a good section on quantifying annotator uncertainty. Ties in to of what I have been thinking about lately, i.e., how to encode natural labeling ambiguity and quality for supervised learning algos
 Reply      Retweet        Like     7    

More by:   Sebastian Raschka
zoom in  
 















  More from:  

Tengyu Ma
Assistant Professor at Stanford, working on machine learning, deep learning, reinforcement learning, representation learning, and their theory.

DeepMind
Our team research and build safe AI systems. We're committed to solving intelligence, to advance science and humanity.

Sebastian Raschka
Author of the 'Python Machine Learning' book. Tweet about Python, deep learning research, open source. Asst Prof of Statistics @UWMadison. Opinions are my own.

Google AI
Google AI is focused on bringing the benefits of AI to everyone. In conducting and applying our research, we advance the state-of-the-art in many domains.

Raquel Urtasun
Founder & CEO @Waabi_ai Professor at @UofT Co-Founder @VectorInst