Robocrunch        AI

Tom Goldstein   @tomgoldsteincs

Associate Professor at Maryland. I want my group to do theory and scientific computing but my students don’t listen to me so I guess we do deep learning 🤷‍♂️
tomgoldsteincs 22.0


  Tweets by Tom Goldstein  

Tom Goldstein    @tomgoldsteincs   ·   9/14/2021
A dragonfly responds to prey in 50 milliseconds using a neural circuit that is about 3 layers deep (10ms per layer, plus time for eyes and muscles to respond). That right there is some fancy network pruning. https://t.co/2qCOJWACyF
 Reply      Retweet   2      Like     1    



Tom Goldstein    @tomgoldsteincs   ·   7/9/2021
We demonstrate this recurrent approach on three problems that are traditionally solved by classical algorithms: prefix sum computation, mazes, and chess. A system trained only on “easy” instances can solve “hard” instances at test time, provided it can think for longer.
 Reply      Retweet   2      Like     30    



Tom Goldstein    @tomgoldsteincs   ·   7/9/2021
After training on small/easy problems, the power of the network can be increased at test time just by turning up the number of iterations of the recurrent unit. By “thinking for longer” the network assembles its knowledge into more complex strategies.
 Reply      Retweet   2      Like     34    



Tom Goldstein    @tomgoldsteincs   ·   7/9/2021
My lab is building neural nets that emulate human “thinking” processes. They increase their intelligence after training by increasing their compute budget. By doing so, a net trained only on “easy” chess puzzles can solve “hard” chess puzzles without having ever seen one…
 Reply      Retweet   195      Like     973    



Tom Goldstein    @tomgoldsteincs   ·   6/12/2021
Code is now available for SAINT - attention networks for tabular data. https://t.co/1IcjHJWCQr
 Reply      Retweet   8      Like     37    








 
  Relevant People  


Yann LeCun
Professor at NYU. Chief AI Scientist at Facebook. Researcher in AI, Machine Learning, etc. ACM Turing Award Laureate.
Yann LeCun 58.4

François Chollet
Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Opinions are my own.
François Chollet 58.2

Stanford HAI
Advancing AI research, education, policy, and practice to improve the human condition.
Stanford HAI 47.5

Andrew Gordon Wilson
Machine Learning Professor
Andrew Gordon Wilson 39.3

Zach Mueller
Always Learning | I stream things occasionally https://t.co/UpZIajLBBl | https://t.co/ceuhjZulbp | Deep Learing Software Engineer | https://t.co/Y32cxGX95d
Zach Mueller 29.1

Simone Scardapane
I fall in love with a new #machinelearning topic every month 🙄 Researcher @SapienzaRoma | Chairman @iaml_it | Co-host @SmarterPodcast | @GoogleDevExpert
Simone Scardapane 28.0

Tom Goldstein
Associate Professor at Maryland. I want my group to do theory and scientific computing but my students don’t listen to me so I guess we do deep learning 🤷‍♂️
Tom Goldstein 22.0