A nice work about universality from Loek

The capstone project of my PhD is now online 🤯 biorxiv.org/content/10.110… We argue that the cortex and striatum accumulate evidence in a distributed manner, with recurrent interactions helping to rescue computation upon perturbations.

If you still don’t know what you’re doing Friday at #ICML2024, I’m going to suggest our HiLD workshop, which pulls together theorists and empiricists to understand training dynamics and how models learn structure and reasoning!

It’s today ICML Conference 25.07 Thursday 11.30-13.00 #1407 Come and chat! w/Stefano Sarao Mannelli - Hiring! Andrew Saxe

Only 3 days left to apply to join my group Chalmers University of Technology as a PhD student: deadline July 31st. Work with me to uncover the mechanisms behind bias generation and amplification in ML! 🔗 chalmers.se/en/about-chalm…

Today is my first time #CCN2024. I'm very excited and mildly jetlagged! I'll be presenting two works: 📃B51 On compositional generalisation and curriculum learning; 📃C93 A framework for modelling critical learning. Looking forward to some feedback and follow-up ideas! 👇

What is the nature of sensory prediction error signals in the neocortex? Our research published in nature reveals that these error signals are amplified responses to unexpected inputs, mediated by a cooperative thalamocortical circuit mechanism! 1/4 nature.com/articles/s4158…

Puh, we have been preparing the new release of the sbi toolbox for quite a while now, and I am really glad to see it out now! Have a look, there are a lot of cool new features! 🚀

Excited that the preprint for the work from my first two years of PhD at summerfieldlab @summerfieldlab.bsky.social is out! In this work, we examine the role of action prediction errors (APEs) in cognitive control: osf.io/5ezxs (1/4)

Congrats all, great work! 👏👏

Looking at linguistic compositionality in LM with representational geometry! It was fun working with the whole team ;)

If you are at #sfn2024, come check poster M17 this afternoon to see how we used gated deep neural networks and all-optical experiments during learning to unveil a new role of cortical serotonin. A collaboration between Andrew Saxe Stefano Sarao Mannelli Butt Lab - Oxford Adam Packer and Trevor Sharp

Gabi is presenting our (mostly his) incredible work on serotonin modelling with gated NNs at #SfN24. Our model replicates existing findings and predicts outcomes in associative tasks, as well as reversal learning tasks under psychedelics—readily validated by Gabi in mice! 🐭🧠

A post-SfN reflection: The social dynamics at SfN poster sessions are always fascinating. But also sometimes frustrating. e.g.: A trainee in my lab (woman) mentioned noticing presenters ignoring her whenever there were other men at the poster. 😞 1/3