Sebastian Riedel    @riedelcastro     10/12/2021
Thinking of throwing more parameters at your few-shot problem? Consider a-few-more-shots instead---with the added side benefit of learning more about your problem! Unless you working on "Open Tasks", but in which case I recommend non-parametric techniques!
 Reply      Retweet   12      Like     67    

More by:   Sebastian Riedel
zoom in  

  More Tweets  

Yuandong Tian    @tydsh     9/17/2021
FAIR MPK Reinforcement Learning (RL) team has full-time research scientist opening. We study fundamental research problem in ML/RL-guided optimization and its real-world applications. Look for candidates in RL, optimization, and representation learning. POC:
 Reply      Retweet   28      Like     145    

More by:   Yuandong Tian
zoom in  

Aleksa Gordić    @gordic_aleksa     7/2/2021
[馃帴馃敟: video - "Multimodal Few-Shot Learning with Frozen Language Models" from @DeepMind ] YT: Few-shot learning powers of big LMs transferred to the multimodal setup (text + vision)! @jacobmenick @serkancabi @arkitus @OriolVinyalsML @FelixHill84
 Reply      Retweet   6      Like     46    

More by:   Aleksa Gordić
zoom in  

OpenAI    @OpenAI     9/23/2021
We want our AI systems to be aligned with human intentions. This is especially important as tasks get more difficult to evaluate. To develop techniques to address this problem, we trained a model to summarize books.
 Reply      Retweet   7      Like     32    

More by:   OpenAI
zoom in  

David Duvenaud    @DavidDuvenaud     9/27/2021
@xkcd covered another reason to dislike "epistemic uncertainty", which is that it sounds like an exotic philosophy problem, instead of plain old uncertainty about parameters.
 Reply      Retweet        Like     17    

More by:   David Duvenaud
zoom in  

  More from:  

Sebastian Riedel
Researcher in NLP/ML @ucl_nlp and @facebookai research, co-founder @factmata, @ELLISforEurope fellow

Yuandong Tian
Research Scientist and Manager in FAIR (Facebook AI Research)

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.

Gael Varoquaux
Research & code: Research director @inria ►Data, Health, & Computer science ►Python coder, (co)founder of @scikit_learn & joblib ►Art on @artgael ►Physics PhD

Stanford HAI
Advancing AI research, education, policy, and practice to improve the human condition.