🔥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

Join us in beautiful Santa Barbara! We're hiring a full-time junior specialist/research technician to play a central role in data collection & analysis of brain imaging studies of pregnancy & menopause. Learn more & apply at: recruit.ap.ucsb.edu/JPF02974 Or help us spread the word💫

1/10 🧵 🔍Can weight symmetry provide insights into sparse training and the Lottery Ticket Hypothesis? 🧐We dive deep into this question in our latest paper, "Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry", accepted at #ICML2025

Very excited to see this out and very lucky to have gotten to be a part of this awesome project!

Amazing to see this out in print!! Many years in the making. Check out this great 🧵 from Michael Goard for all the details

Online now: The estrous cycle modulates hippocampal spine dynamics, dendritic processing, and spatial coding dlvr.it/TKlQHJ

Apply or retweet! :-)

Really happy to see this paper out, led by Nishil Patel in collaboration with Stefano Sarao Mannelli and Andrew Saxe: we apply the statistical physics toolbox to analyse a simple model of reinforcement learning, and find some cool effects, like a speed-accuracy trade-off for generalisation 🚀

Ever wanted to try topological deep learning but felt overwhelmed by the complexity? 👉 Meet TopoTune: a plug-and-play framework that turns any graph neural networks into a topological one! Mathilde Papillon🦋 mathildepapillon .bsky .social Guillermo Bernárdez Claudio Battiloro 🦋 @clabat9.bsky.social Geometric Intelligence Lab Real AI @ UCSB UCSB ECE

I am very excited about our new paper just published in PNAS. Dense Associative Memory is a versatile family of models that allows to store large amounts of information, have strong error-correcting capabilities, and other desirable properties. But is it possible to build it in

An awesome collaboration with Aran Nayebi, led by the amazing Reece Keller! The neural-glial circuit underlying futility integration in larval zebrafish naturally emerges in intrinsically motivated, embodied agents. See their excellent threads (and the preprint) for the details!

Welcome Vineeth! We're hiring across the board to build the best data engine for AI. Come join us! jobs.ashbyhq.com/datologyai

MAHA: Make America Hungry Again

Very happy to see a Transmitter (The Transmitter) piece on our recent work on estrous cycle modulation of hippocampal structure and function. Thanks to Sydney Wyatt (Sydney Wyatt) for covering the work and its context: thetransmitter.org/neuroendocrino…

📷 3-Year Postdoc in Cognitive Neuroscience at @BottiniLab, CIMeC, University of Trento! 📷 Memory, attention, eye movements, and cognitive maps INFO: drive.google.com/file/d/1WGEEpl… DEADLINE TO APPLY JULY 9TH - BUT FLEXIBLE START AT END 2025 OR SPRING 2026!

You're into neuroscience and AI? 🧠 🤖 You're working on the mathematics that drives biological and artificial neural networks? We want to hear from you! Submit to NeurReps 2025 at NeurIPS Conference! 📅 Deadline: Aug 22 📄 Two tracks: 9p proceedings & 4p extended abstracts

Foundational models collect all the data from all available instances of the process (e.g. language) to parametrize input to output relationships - interpolatively, with no real time updates. In contrast, the human brain collects data individualized to the process from relatively