Johan Mathe
@johmathe
Followers
486
Following
67
Statuses
90
Builder - applied maths, optimization and climate science.
Berkeley, CA
Joined May 2009
RT @tarinziyaee: Remember Moravec's paradox? "Corner cases". "Long tails". You can play whack-a-mole with them. Or, you can confront t…
0
29
0
RT @mathildepapillo: This should be fun! I'll be sharing our recent literature review on all things geometric/topological/algebraic ML✨🍩 Wi…
0
13
0
RT @johannbrehmer: Does equivariance matter when you have lots of data and compute? In a new paper with Sönke Behrends, @pimdehaan, and @T…
0
61
0
RT @mathildepapillo: What if any neural network could go topological? While being just as (or more) general, equivariant, and expressive as…
0
52
0
RT @SMataigne: Thrilled to announce that our work about "Bispectrum convolutional layers" for cheap and efficient Group-Invariant NN has be…
0
5
0
If you are attending ICML don’t miss @ninamiolane’s presentation on AI/ML/Topological and Algebraic structures. She is unmatched at making these fairly abstract concepts feel so clear, tangible and useful! On top of this the visuals (slides, tables) are next level. Again big thanks to @naturecomputes , @mathildepapillo D. Buracas @cashewmake2 @hansenlillemark @AbbyBertics and X. Pennec!
Looking forward to the @GRaM_org_ workshop #ICML2024 !🌟 I'll present a guide to AI/ML with geometric, topological & algebraic structures. W/ @naturecomputes @johmathe @mathildepapillo D. Buracas @hansenlillemark @cashewmake2 @AbbyBertics X. Pennec.
2
5
29
RT @mathildepapillo: Building these structures into ML models makes them more efficient, accurate, and robust💪 We classify and illustrate s…
0
7
0
Thanks @maurice_weiler! Let us know if you see other relevant papers to add to the review down the line :)
Amazing overview paper on geometric deep learning with lots of visualizations 👏 Great to see that people are not only working on new models, but rather investigate how all the methods out there relate!
1
3
11