🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Yes. And it’s called saving lives.

This is my last tweet. The more I learn about Musk’s projects the less I want to associate with any of them. DCD

It’s time for my first tweet print! Presented at CCN2023 w/ Sushrut Thorat Peter König Tim Kietzmann “Diagnosing Catastrophe: Large parts of accuracy loss in continual learning can be accounted for by readout misalignment” arxiv.org/abs/2310.05644 🧵1/12

Loving this.

The new Braindecode version is out! This version resulted from a wonderful code sprint that Moreau Thomas, Robin Tibor Schirrmeister, Alexandre Gramfort, Denis A. Engemann, Sylvain Chevallier, and I organized last summer! + the regular contributions received on our library :)

You don't have any "values." Those are a malign myth—the hypothetical axioms of a first-principles ethical/motivational system from which, in the rationalist imagination, concrete judgements derive. I keep saying this without explanation; here's a bit from Miya Perry:

The "Ship of Theseus" article has been edited 1792 times since it was created in July of 2003. At present, 0% of the phrases in the original article (seen below) remain.

Our account has lost over 7,000 followers in December. We continue to ask for your engagement. You create this incredible community and help us keep the memory alive. Support Auschwitz Memorial and amplify our voice.

Excited to announce the second iteration of NEAT (Neuro-AI-Talks), which will take place September 2nd-3rd 2024 in Osnabrück. kietzmannlab.org/neat2024 Never heard of it? Let me tell you what this is about 🧵

🚨 Looking for a postdoc/research-scientist/lecturer position in the UK 🇬🇧, mid-2025! Q: How does the visual cortex acquire its expressivity (SSL/RL), process visual relations, and interface with decision-making networks? #NeuroAI #CogSci #CompNeuro CV: sushrutthorat.com/assets/cv-full…

David had a great idea: train people to expect a stimulus, and then, upon violating said expectation, he modeled the brain response by the divergence in different layers of a visual ANN. Later layer differences explained the signal in EVC better than early layer differences.

Using a BCI to white-box visual attention during perceptual decision making. Great stuff and fond memories of my time at Cognition ENS.

We have an opening for a postdoc to work on a collaborative project with Máté Lengyel (UCambridge Engineering) combining machine learning methods with human experiments on visual perception and memory jobs.cam.ac.uk/job/49299/

Scared to share this after 10 freaking years of waiting but here we go: We found that temperature *perception* can change the next generations, even when “it’s just in the parents' head”. Read how C. elegans neurons control epigenetic inheritance! biorxiv.org/content/10.110…

Where do #color categories come from? It's a very old question. Color is a continuous parameter, yet we categorize it. Since ancient times, there have been 4 consensus "basic" color categories: red, yellow, green, & blue. Are these hard-wired in our brains? 1/

Now out in Nature Human Behaviour Nature Human Behaviour: “End-to-end topographic networks as models of cortical map formation and human visual behaviour”. Please check our NHB link: nature.com/articles/s4156…

I'm thrilled to see this preprint out! Lenny compellingly demonstrates, in a data-driven way, a coding scheme unifying distributed dimensions & category selectivity.➡️Higher visual cortex comprises many partially overlapping tuning maps that include but go beyond category tuning!

Exciting new preprint from the lab: “Adopting a human developmental visual diet yields robust, shape-based AI vision”. A most wonderful case where brain inspiration massively improved AI solutions. Work with Zejin Lu | 陆泽金 Sushrut Thorat and Radoslaw Cichy arxiv.org/abs/2507.03168

🚨 SOTA shape-biased ANNs, that experienced their datasets through the developing eyes of humans (from birth to 25 year olds). There's still hope for cognitive (neuro)science knowledge equipping ANNs with cool new abilities which seem elusive from the pov of ML research.