Blake Richards (@tyrell_turing) 's Twitter Profile
Blake Richards

@tyrell_turing

Researcher at @mcgillu combining AI and neuroscience. Also on Bluesky (@tyrellturing.bsky.social) and Mastodon: @[email protected].

ID: 1375825160

linkhttps://linclab.mila.quebec/ calendar_today24-04-2013 00:53:43

23,23K Tweet

15,15K Followers

1,1K Following

Mila - Institut québécois d'IA (@mila_quebec) 's Twitter Profile Photo

Nouveau conférencier pour “Boussole des politiques en IA”, le 27-28 août! Guillaume Lajoie Guillaume Lajoie, professeur adjoint de l'Université de Montréal, discutera entre autres des façons de renforcer et d’approfondir les concepts de l'IA. mila.quebec/fr/boussole-de…

Nouveau conférencier pour “Boussole des politiques en IA”, le 27-28 août! Guillaume Lajoie <a href="/g_lajoie_/">Guillaume Lajoie</a>, professeur adjoint de l'<a href="/UMontreal/">Université de Montréal</a>, discutera entre autres des façons de renforcer et d’approfondir les concepts de l'IA. mila.quebec/fr/boussole-de…
Melissa & Chris Bruntlett (@modacitylife) 's Twitter Profile Photo

The most ambitious car-free scheme on the continent, Montréal pedestrianized 11 commercial arteries—totaling 9.4 km—in seven boroughs this summer. A pandemic-era initiative pushed by business leaders, they have quickly become cherished destinations for locals and tourists alike.

The most ambitious car-free scheme on the continent, Montréal pedestrianized 11 commercial arteries—totaling 9.4 km—in seven boroughs this summer.

A pandemic-era initiative pushed by business leaders, they have quickly become cherished destinations for locals and tourists alike.
Il Memming Park (@memming) 's Twitter Profile Photo

A new preprint that revives the theory of continous attractors that may be surprising to you! Despite their mathematical fragility, we show that they are functionally *robust*. No wonder we see approximate continuous attractors in neuroscience often. arxiv.org/abs/2408.00109

Mila - Institut québécois d'IA (@mila_quebec) 's Twitter Profile Photo

We are proud to participate with Espace pour la vie VT Ecostudies has migrated. and Université d'Ottawa | University of Ottawa in the launch of the #eButterfly application. This free application uses AI to identify butterflies all over the world, and lets you share your observations directly from your phone. Read the press

We are proud to participate with <a href="/EspacePourLaVie/">Espace pour la vie</a>  <a href="/VTEcostudies/">VT Ecostudies has migrated.</a> and <a href="/uOttawa/">Université d'Ottawa | University of Ottawa</a> in the launch of the #eButterfly application. This free application uses AI to identify butterflies all over the world, and lets you share your observations directly from your phone. Read the press
Danilo Bzdok (@danilobzdok) 's Twitter Profile Photo

New research from our lab, led by Karin Saltoun: #brain #asymmetry changes *within-subjects* over years, which explains individual differences in i) everyday behavior and ii) vulnerability to disease; demonstrated at population scale preprint: researchsquare.com/article/rs-479…

New research from our lab, led by <a href="/KarinSaltoun/">Karin Saltoun</a>:

#brain #asymmetry changes *within-subjects* over years, which explains individual differences in i) everyday behavior and ii) vulnerability to disease; demonstrated at population scale

preprint: researchsquare.com/article/rs-479…
Your man on the inside (@insidertakes) 's Twitter Profile Photo

She’s gonna publish a dozen papers on the internet’s reaction to her terrible breakdancing. This woman is playing 5D chess on an academic scale.

Dan Levenstein (@dlevenstein) 's Twitter Profile Photo

The degree of rigor by Colin (et al) to formalize what’s meant by “biologically plausible” in terms of locality (TL;DR which variables have access to which other variables) is quite impressive, and worth thinking through for anyone interested in neuro/AI.

Patrick Mineault (@patrickmineault) 's Twitter Profile Photo

What are foundation models in neuroscience? I'll be giving a talk next week to the NIH neuroscience ethics working group. I started writing a short blog post which snowballed into this 5,000 word essay neuroai.science/p/foundation-m…

Stanislav Fort (@stanislavfort) 's Twitter Profile Photo

✨🎨🏰Super excited to share our new paper Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on vLLMs 1/12

Surya Ganguli (@suryaganguli) 's Twitter Profile Photo

A fun a16z Bio + Health podcast w/Vijay Pande & Bowen Liu on AI and drug discovery covering, among other things, foundation models in biology, LLMs for small molecules, clinical trial opt, evolution and AI, and many opportunities for AI powered efficiency in drug design

Jonathan (@jhcornford) 's Twitter Profile Photo

Why does #compneuro need new learning methods? ANN models are usually trained with Gradient Descent (GD), which violates biological realities like Dale’s law and log-normal weights. Here we describe a superior learning algorithm for comp neuro: Exponentiated Gradients (EG)! 1/12

Why does #compneuro need new learning methods? ANN models are usually trained with Gradient Descent (GD), which violates biological realities like Dale’s law and log-normal weights. Here we describe a superior learning algorithm for comp neuro: Exponentiated Gradients (EG)! 1/12
Raymond Chua (@raymondrchua) 's Twitter Profile Photo

It’s been a long time coming, but I’m thrilled to share my first research paper with Arna Ghosh , Christos Kaplanis, Blake Richards, and Doina! Just accepted to NeurIPS 2024 (see u in Vancouver! 🇨🇦). This will be a longer thread—thanks for following along! arxiv.org/abs/2410.22133 1/11

Mehdi Azabou (@mehdiazabou) 's Twitter Profile Photo

How can large-scale models + datasets revolutionize neuroscience 🧠🤖🌐? We are excited to announce our workshop: “Building a foundation model for the brain: datasets, theory, and models” at CosyneMeeting #COSYNE2025. Join us in Mont-Tremblant, Canada from March 31 - April 1.

How can large-scale models + datasets revolutionize neuroscience 🧠🤖🌐? We are excited to announce our workshop: “Building a foundation model for the brain: datasets, theory, and models” at <a href="/CosyneMeeting/">CosyneMeeting</a> #COSYNE2025. Join us in Mont-Tremblant, Canada from March 31 - April 1.