Geometric Intelligence Lab
@geometric_intel
Followers
3K
Following
1K
Media
28
Statuses
1K
Research lab at @UCSBEngineering revealing the geometric signatures of natural and artificial intelligence | PI: @ninamiolane
Santa Barbara
Joined September 2021
🌟 New review from the lab! Discover the geometric, topological and algebraic signatures of machine learning and deep learning models. By @naturecomputes @johmathe @mathildepapillo D. Buracas @hansenlillemark @cashewmake2 @AbbyBertics X. Pennec & @ninamiolane !
In the 20th century, non-Euclidean geometry transformed how we model the world with pen and paper. In this century, it’s revolutionizing how we model the world with machines. Our review on the topic is out https://t.co/zSDLIV8Ghw, led w the brilliant @naturecomputes @johmathe
1
47
169
UPDATE 🌧️ Because of the unfortunate rain set for tomorrow, we will be rescheduling @fatihdin4en's talk for next Thursday (Nov. 20) at 7pm at Brass Bear Brewing
Rumor has it Mother Nature might be the best AI engineer🌱💡 Come see why at Brass Bear Brewing, Nov 13 @ 6pm. With Dr. Fatih Dinc, we’ll dive into how brains, bots, and biology compute with intelligence
0
3
12
Rumor has it Mother Nature might be the best AI engineer🌱💡 Come see why at Brass Bear Brewing, Nov 13 @ 6pm. With Dr. Fatih Dinc, we’ll dive into how brains, bots, and biology compute with intelligence
0
12
24
Huge congrats to @SMataigne and P.-A. Absil on two new papers out this month! 🎉 Bringing elegant math to life through algorithms on the Stiefel manifold and Riemannian barycenters🌐
Thrilled to see these two papers by @SMataigne co-authored with P.-A. Absil published this month 🤩 They connect deep mathematical theory to practical algorithms on the Stiefel manifold and the approximation of the Riemannian barycenter 🌐 Details & papers👇@geometric_intel
0
0
5
The second paper called "On the Approximation of the Riemannian Barycenter" uses the bounds from the above article to compute approximations of the Riemannian barycenter at very low computational cost! https://t.co/ARw2prN8vK
1
2
5
The first paper called "Bounds on the geodesic distances on the Stiefel manifold for a family of Riemannian metrics" studies the geometry of the Stiefel manifold to derive simple and insightful bounds on the computationally untractable geodesic distance. https://t.co/xWwD0pkVAf
1
2
9
🚀Don’t miss out on the Topological Deep Learning Challenge 2025! 20 days left to submit – more than enough time to make your mark🍩 👇See details and prize info below🌟 @geometric_intel @UCSBengineering @ucsantabarbara @EPFL @mathildepapillo @gbg1441 @lev_telyatnikov
🚨 20 DAYS LEFT to submit to the Topological Deep Learning Challenge! TopoBench just hit 200 stars 🌟, and we're looking forward to seeing your submissions before the deadline. This year's challenge has multiple ways to contribute and prizes. All details: https://t.co/JDRgKVmOAH
0
3
3
This is the final 20-day countdown! Our step-by-step tutorial makes it easy to get started, especially for dataset contributions (Mission A), which can be added in just a couple of hours. Check the tutorial and submit your work:
0
4
6
Do you have ideas for new tasks within TDL? Or a completely new challenge of your own? Then Mission B, Category B.2 is for you: Pioneering New TDL Benchmark Tasks! We want to see your most creative and impactful ideas.
1
3
6
Are you interested in large-scale Topological Deep Learning? We are too! That's why Mission B, Category B.1 is focused on Advancing the Data Infrastructure. This is your chance to make TDL more scalable and robust.
1
3
6
"But I don't have a novel dataset!" No problem! Mission A is all about growing the TopoBench ecosystem. Datasets are NOT required to be novel. If you have topological data, make it available within TopoBench to compete. It's that simple!
1
3
5
As a reminder, we have incredible prizes for winners, graciously offered by our partners: 💰 Win cash prizes up to $800 USD from #ArlequinAI 🎓 Secure prestigious internships: @UCSB (for PhD students) @EPFL (for Master's students)
1
3
5
Details on our research and how to apply to our lab are on our website: https://t.co/UE05mo7GZ2👋
@UofCalifornia @ucsantabarbara @ucsbece @ucsbcs
gi.ece.ucsb.edu
The mission of the Geometric Intelligence Lab is to reveal the geometric signatures of natural and artificial intelligence.
0
0
1
And yes, we do play volleyball on the beach nearby🏐🌴
1
0
0
🚀We’re recruiting PhD students for 2026! If you’re passionate about uncovering the geometric signatures of intelligence in brains🧠 and AI🤖, we’d love to hear from you! Join us in exploring the computations that power natural and artificial minds. 🌐✨
I am recruiting PhD students for 2026!😃 You want to reveal the geometric signatures of natural and artificial intelligence, and understand computations in brains and AI? 🌐🧠🤖 Apply to the UCSB Geometric Intelligence Lab ✨ This is the view you'd have from... your desk🌴
2
2
10
Details on our research and how to apply to our lab are on our website: https://t.co/LfCXn07g4b. We hope to hear from you! 👋 @UofCalifornia @ucsantabarbara @ucsbece @ucsbcs @geometric_intel
gi.ece.ucsb.edu
The mission of the Geometric Intelligence Lab is to reveal the geometric signatures of natural and artificial intelligence.
1
3
31
From your desk you'll see dolphins, beach volleyball courts, a great surf spot, & more importantly: your passionate, kind, & smart colleagues. @gbg1441 @hopfbifurcator @helloyesimsarah @AdeleMyersPhD @louisacornelis @AbbyBertics @mathildepapillo Luis Pereira Alex West
2
7
44
You are specifically interested in AI? 👉 Look at the AI Curriculum from the UCSB Real AI Initiative offered within the CS and the ECE departments. https://t.co/vFgctJUtwe
@ai_ucsb @ucsbcs @ucsbece
ai.ece.ucsb.edu
4
5
31
We are physicists, neuroscientists, mathematicians and computer scientists who study intelligence in biological and artificial neural networks and use our findings to build better AI models. 👉You can join us via the ECE, CS, Math or DYNS programs!
1
5
44