Interested in affordances and virtual reality? Apply to our PhD program to join my lab! Details: sites.google.com/view/paclab/pr…

Very proud of this fresh new paper: pt.ffri.hr/pt/article/vie… Kudos to Landry Filce (honors student) and Morteza Mahdiani ! USM PAC Lab @BrainBehavUSM Free to download - thank you to the editorial board and reviewers at Psihologijske teme ! @RiCogSci

If you are a graduate student working in AI/ML and are anxious and overwhelmed by all the recent hype, get off Twitter. It's your advisor's job to filter out all the hype and keep you focused on what really matters.

Years in the making: 304 papers cited in a huge effort to characterise this emerging field that we hold dearly. Read this paper to find out what we are doing, why and how, and why we think that ANNs are a central tool for understand brain computations. #neuroconnectionism

Our lab 🐌now has a website and a logo: snailab.ca Check out our website to learn more about our approach and research goals. Big thanks to the great artist and neuroscientist Maria Zamfir, PhD for helping with the logo.

My deep learning course UNIGE_en is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch. fleuret.org/dlc/ And my "Little Book of Deep Learning" is available as a phone-formatted pdf (400k downloads!) fleuret.org/lbdl/

Compute is all you need. For a given amount of compute, ViT and ConvNets perform the same. Quote from this DeepMind article: "Although the success of ViTs in computer vision is extremely impressive, in our view there is no strong evidence to suggest that pre-trained ViTs

1/ 🤖 New paper hot off the press 🐜 Automated behavioural analysis using machine learning is great, but still needs lots of effort to curate training data. What if a computer could generate that data for you? Say hello to replicAnt nature.com/articles/s4146… #OpenSource

Do you use the correlation coefficient in your #MachineLearning? covariance matrices, PCA, variance additivity, feature ranking, multicolinearity, etc., it's everywhere! My #Python interactive Matplotlib #dashboard is a warning - the impact of outliers on correlation! On

My favorite Gemini demo:

This paper from Daniel Yamins and Kalanit Grill-Spector looks pretty cool, CC Shahab Bakhtiari (in-line with your work): biorxiv.org/content/10.110…

On the emergence of specialized streams in neural networks: 1/ specialization can emerge without task-specific optimization. Self-supervised learning, as shown in the recent work by Dawn Finzi et al and our previous work, can lead to emerged specialized streams.

New Bishop "Deep Learning" book is available free at the bottom of this page. bishopbook.com (Although I bought a copy, because I need to convey gravitas)

Have you used transformers but not fully grasped how they work internally?👀 Welcome the Random Transformer, a step-by-step walkthrough doing the math of the transformer model. Kick off your year understanding what's going on under the hood. osanseviero.github.io/hackerllama/bl…

Last November, we organized a workshop at Mila - Institut québécois d'IA on GFlowNets. All the videos are now available online. If you want to learn more about GFlowNets and their applications, check out this blog post: mila.quebec/en/gflownets_a…

Some examples of how models of the visuomotor system have changed over the course of my 30+ yr. career in neuroscience (from a recent keynote).

# CUDA/C++ origins of Deep Learning Fun fact many people might have heard about the ImageNet / AlexNet moment of 2012, and the deep learning revolution it started. en.wikipedia.org/wiki/AlexNet What's maybe a bit less known is that the code backing this winning submission to the

Our new work on CLIP is out now! Explore how it predicts fine-grained knowledge about manipulable objects.

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

This is perhaps the most important paper I've contributed to so far. Also the one with most ups and downs. Years in the making. Several rounds of review in many outlets. But it's out now. Thanks to Adrien Doerig who really drove that thing home. Enjoy! nature.com/articles/s4225…