It took me a few years since the last article, but I wrote a new blog piece. This time on the connection between differentiation and rooted trees: danielewworrall.github.io/blog/2023/11/r…

Excited to share Rotating Features – accepted as oral at #NeurIPS2023 Rotating Features learn to represent object affiliation via their orientation on real-world data without labels. Let’s dive in! 📜 arxiv.org/abs/2306.00600 🖥️ github.com/loeweX/Rotatin…

This is the 2nd post in our series on equivariant neural nets. It explains conventional CNNs from a representation theoretic viewpoint and clarifies the mutual relationship between equivariance and spatial weight sharing. maurice-weiler.gitlab.io/blog_post/cnn-… 👇TL;DR🧵

This "engineering viewpoint" establishes the implication weight sharing -> equivariance Our representation theoretic viewpoint turns this around: weight sharing <- equivariance It derives CNN layers purely from symmetry principles! [4/N]

I’m happy to share that I started a new position as a Research Scientist at @nvidia working alongside @liu_mingyu, @arunmallya and many other amazing researchers! I am extremely excited about this new oportunity 😃! More info about the team: research.nvidia.com/labs/dir/

@geometric_intel @naturecomputes @cashewmake2 Congrats! Well deserved for your already amazing research and vision for the field, @naturecomputes and @cashewmake2 ! Looking forward to seeing what else you manage to pull off the next years :D

✨Amsterdam's exceptional scientist is one of the recently appointed ELLIS Scholars Congrats, @erikjbekkers 🚀 ivi.fnwi.uva.nl/ellis/2023/11/… #ELLISforEurope #ELLISunitAmsterdam #AI #ML

I am recruiting PhD students for 2024!😃 You want to reveal the geometric signatures of natural and artificial intelligence, and crack the neural code? 🌐🧠🤖 Apply to the UCSB Geometric Intelligence Lab✨ This is the view you'd have from... well, your desk🌴

1st post in a series accompanying our book on equivariant CNNs. It is meant to give an easy intro to the main concepts/intuitions behind equivariant DL. I explain *what* equivariant NNs are, *why* they are desirable, and *how* to construct them. maurice-weiler.gitlab.io/blog_post/cnn-… 👇TL;DR🧵

Today at a workshop organized by @egavves and @Ellis_Amsterdam, @erikjbekkers talked about geometry, equivariance and neural ideograms! Fascinating talk, and a world record of citing a person ~2h after his talk 😂

For the free online @LogConference we have a bunch of free local meetups! Find out if there is one close to you. Links to some of them are in the reply 👇 1/3

✨PhD vacancy alert✨ Daan Pelt and I are looking for someone that wants to work with us on generative modelling of shape and geometry! * Position at @AmlabUva & @LIACS. * Apply before 3 Nov! * Apply here: vacatures.uva.nl/UvA/job/PhD-Po… * Part of the HI project: hybrid-intelligence-centre.nl

The code for E(n) Equivariant Simplicial Message Passing Networks (ICML, 2023) has been released 🦦 Code: github.com/flooreijkelboo… ArXiv: arxiv.org/abs/2305.07100 Thanks again to Rob and @erikjbekkers for the collab :D

We proudly present our 524 page book on equivariant convolutional networks. Coauthored by Patrick Forré, @erikverlinde and @wellingmax. maurice-weiler.gitlab.io/#cnn_book [1/N]

✨PhD vacancy alert✨ Daan Pelt and I are looking for someone that wants to work with us on generative modelling of shape and geometry! * Position at @AmlabUva & @LIACS. * Apply before 3 Nov! * Apply here: vacatures.uva.nl/UvA/job/PhD-Po… * Part of the HI project: hybrid-intelligence-centre.nl

Our paper has been accepted as an oral to @NeurIPSConf ! 😃🥳 📜Updated paper at arxiv.org/abs/2305.11141 💻Updated code (including Colab tutorial) at github.com/DavidRuhe/clif… twitter.com/djjruhe/status…

Layer-wise equivariance symmetries (e.g. conv layers) allow neural nets to generalise effectively. But can we learn them automatically using gradients? We show we can! Excited to share that our method ELLA has been accepted as a spotlight paper at #neurips2023. A thread.👇1/11🧵

How can we simplify the designing of equivariant neural networks and make them more expressive? In this paper, recently accepted to NeurIPS 2023, we develop implicit steerable kernels to answer this question! 📰: arxiv.org/abs/2212.06096 💻: maxxxzdn.github.io/blog/implicit_… 🧵1/10

📣Come and deep dive into the cutting-edge research at the Delta Lab 2 Showcase 🚀   📆 Monday, 23 Oct 2023 📍 UvA Science Park H0.08 ⏰ 09:30-12:00 🔗 forms.office.com/e/0HnYp31TG5 (before 10 Oct) @BoschGlobal @UvA_Amsterdam #ML #AI #ComputerVision

Very grateful for this wonderful opportunity from @SimonsFdn! I will be using the fellowship to work on problems in geometric deep learning with @erikjbekkers. twitter.com/SimonsFdn/stat…

@nblqbl @SimonsFdn Congrats Nabil. I'm really excited about this and am looking forward to doing research with you! Theoretical physics + geometric deep learning is such a great match!

Our blog post on scaling spherical CNNs for scientific applications was just published, check it out! twitter.com/GoogleAI/statu…

☄️Tutorial Inbound!! We know that a rotated Boot is still a Boot.👞🥾 How can we use this info to design Neural Networks? 👥Reference: Group Equivariant Convolutional Networks, 2016 by @TacoCohen @wellingmax t.ly/CKBB7 👀Full video here: t.ly/qu1Wd

Some fresh ideas at the Visual Inductie Priors workshop @VIPriorsICCV , Questioning the current trend of scaling up the data and model. @ICCVConference #ICCV

A little late for the party, but I am truly excited that our work on "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields" was accepted at @NeurIPSConf! 😊 Wonderful collaboration with @erikjbekkers, @nsn86, and @egavves. Details & source code coming soon!

🥳 So excited our newest paper on multimodal machine learning for prediction of ICD-non benefit is out now at @EuropaceEiC @ESC_Journals !! 🙏Thanks to our amazing team: led by @kolk_maarten - @S_NarayanMD @sruiperez98 @KnopsReinoud @erikjbekkers & many! academic.oup.com/europace/artic…

Wondering if I should generate my academic website using a language model that summarizes my recent papers, and runs regularly on a cronjob... Thus pre-empting the professor's out-of-date website meme

@sibasmarak Haha, Pleasure was all mine! Loved the discussion and can't wait to see your upcoming publications!

Interested in differential geometry for machine learning and deep learning?🤩 Interested in learning how to use, or contribute to, the software @geomstats ?🌐 github.com/geomstats/geom… If you are at GSI23 in Saint Malo, come see us at lunch time in Vauban room!👋💻

"Riemannian geometry for efficient analysis of protein dynamics data" Authors claim this approach "performs exceptionally well on coarse-grained molecular dynamics simulated data" Paper: arxiv.org/abs/2308.07818 Github: github.com/wdiepeveen/Rie…