🔥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

Our preprint is out!🚀 We explore attractor mechanisms that subserve short-term memory by training 35,000+ recurrent neural networks! Most importantly, we present a phase diagram that reveals how learning rate & delay length shape attractor dynamics. 👉arxiv.org/abs/2502.17433

See this work with Bariscan, the new rising star student from Turkey! Here, we show how even simple changes to task or optimization parameters can lead to distinct geometrical solutions. Most interestingly, this is not completely random. Instead, there are phases of algorithms!!

🧵 New paper! We explore sparse coding, superposition, and the Linear Representation Hypothesis (LRH) through identifiability theory, compressed sensing, and interpretability research. If neural representations intrigue you, read on! 🤓 arxiv.org/abs/2503.01824

How can neural nets extract *interpretable* features from data—& uncover new science? 👉 Discover our mathematical framework tackling this question w/ identifiability theory, compressed sensing, interpretability & geometry!🌐 By David Klindt Patrik Reizinger Charlie O'Neill H Maurer

"Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures" (by S Sanborn, J Mathe, M Papillon, D Buracas, HJ Lillemark, C Shewmake, A Bertics, X Pennec, N Miolane): arxiv.org/abs/2407.09468

📢 New Paper Alert! 🚀 Excited to share our latest work, "Ordered Topological Deep Learning: a Network Modeling Case Study", which shows the first state-of-the-art TDL application to a real-world scenario! 📄arxiv.org/pdf/2503.16746 A thread 🧵👇 (1/5)

Last, but not least, OrdGCCN sets the stage for future TDL-driven applications in fields requiring sophisticated structures! 💫 Huge shoutout to my great collaborators! Miquel Ferriol, Carlos Güemes, Mathilde Papillon🦋 mathildepapillon .bsky .social, Pere Barlet, Albert Cabellos, Nina Miolane 🦋 @ninamiolane.bsky.social (5/5)

Thrilled to share this new preprint on Ordered Topological Deep Learning🔢🍩 We're turning theory into real-world impact by bringing TDL to computer network studies 🤖 Led by Guillermo Bernárdez w/ Miquel Ferriol, Carlos Güemes, Mathilde Papillon🦋 mathildepapillon .bsky .social Pere Barlet Albert Cabellos &I Details🧵👇

😇Hijacking this great thread to talk about a potential way to _identify_ problems with existing benchmarking datasets (also to appear in ICML 2025): arxiv.org/abs/2502.02379 TL;DR: We look at how "graphical" graph benchmarking datasets are. Spoiler: less than you'd hope for!

Come find me Graph Signal Processing Workshop 2025 Mila - Institut québécois d'IA all week! Can’t wait to be back in Montreal connecting with the community🕸️ I’ll be speaking on purely graph-based (!) Topological Deep Learning first thing tomorrow at 9am. Let’s kick off this workshop in style🍩

Graph Signal Processing Workshop 2025 first day! Started off with an exciting keynote by Mathilde Papillon🦋 mathildepapillon .bsky .social on making GNNs go topological with TopoTune ! see GitHub.com/geometric-inte….

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

Gorgeous tutorial from Mathilde! Check it out!

An absolute must-read! 🚀 Huge congrats to all the authors on this impressive work — definitely worth checking out!

We are looking for reviewers to serve on the Program Committee of the Symmetry and Geometry in Neural Representations (NeurReps) workshop at NeurIPS 2025! If you are interested in participating, please fill out this form: forms.gle/wgUXHT7Mq71nK3… Symmetry and Geometry in Neural Representations

Pregnancy & motherhood transform the brain in ways we're only beginning to understand🧠 We're uncovering these changes with Susana Carmona Magdalena Martínez-García PhD🦋 Emily G. Jacobs 🦋 @emilyjacobs.bsky.social Hannah Grotzinger Kaya Jordan neuromaternal thanks to CZI Science's generous support ! tinyurl.com/38jb7hm6

The era of artificial scientific intelligence is here. As algorithms generate discoveries at scale, what role remains for human scientists?🤔 Thanks PLOS Biology for publishing my perspective Real AI @ UCSB UCSB ECE UC Santa Barbara's College of Engineering UC Santa Barbara ! journals.plos.org/plosbiology/ar…