Fabian Pedregosa
gradientflowing.bsky.social
Fabian Pedregosa
@gradientflowing.bsky.social
Keep the gradients flowing
Reposted by Fabian Pedregosa
Look how awkward I am in front of a camera 🤦🏼‍♀️ But the science we do is great, I swear, get in touch if you'd like more details!
🎞️What is the link between what we know and what we say? The Work Package WorldKnowledge investigates this topic in humans, animals, and even computers. Dive into their #research in this video!

www.youtube.com/watch?v=IoNN...
Linking word knowledge and world knowledge with the WP WorldKnowledge - NCCR Evolving Language
YouTube video by NCCR Evolving Language
www.youtube.com
April 10, 2025 at 3:07 PM
Reposted by Fabian Pedregosa
What do we need, in good as in bad times? A community. Today is as good a day as any to:
✨renew your membership to the Society for the Neurobiology of Language
✨submit an abstract/symposium to #SNL2025
✨ register for one of the member-initiated virtual activities 2025.neurolang.org/virtual-acti...
Member-Initiated Virtual Activities
2025.neurolang.org
February 26, 2025 at 1:49 PM
Reposted by Fabian Pedregosa
Missing from Martin's great recap of #ABIM2025 is his own talk which covered in 30 min ins&outs of representational spaces in behavior, brains, & artificial agents. This edition of ABIM was all-around terrific: check out what you missed (www.unige.ch/ABIM/files/9...) & set a reminder for next year!
January 16, 2025 at 1:47 PM
Reposted by Fabian Pedregosa
Sport was indeed the best part of 2024.
January 1, 2025 at 8:17 AM
Reposted by Fabian Pedregosa
When optimization problems have multiple minima, algorithms favor specific solutions due to their implicit bias. For ordinary least squares (OLS), gradient descent inherently converges to the minimal norm solution among all possible solutions. https://fa.bianp.net/blog/2022/implicit-bias-regression/
December 19, 2024 at 6:00 AM
Finishing a very sporty 2024 in the best possible way #sansilvestre2024 @vborghesani.bsky.social
December 31, 2024 at 6:00 PM
Very nice post from my colleague Rishi Mehta on the different tactics used by AlphaProof during the international math olympiad

rishimehta.xyz/2024/11/17/a...
AlphaProof’s Greatest Hits
Here I’ll try to explain the coolest ideas in each of AlphaProof’s IMO 2024 solutions. AlphaProof produces proofs in Lean, and each Lean proof is composed of a series of tactics. So I’ll pick out the ...
rishimehta.xyz
November 29, 2024 at 10:41 AM
Reposted by Fabian Pedregosa
New essay by DeepMind about AI for scientific discovery, there's a lot of interesting ideas and citations to others's work here
deepmind.google/public-polic...
A new golden age of discovery
In this essay, we take a tour of how AI is transforming scientific disciplines from genomics to computer science to weather forecasting. Some scientists are training their own AI models, while...
deepmind.google
November 26, 2024 at 2:13 PM