Theory of Neural Networks (how the heck do they work?)
Assistant Professor @RWTH
Previous: Postdoc @EPFL, Swartz Fellow @Harvard
Lab: https://avmlab.physik.rwth-aachen.de
Personal: alexvanmeegen.github.io
Background art: https://www.bettina-hachmann.de
Alex van Meegen
Loading...
NEW PAPER. Why do larger networks train better?
"Because they contain more candidate *sub*networks that can learn the task" → lottery tickets
This popular explanation uses an appealing but misleading metaphor🧵
We propose an intuitive alternative grounded in theory: escape dimensions
Every summer I repost this article on how to spot drowning. Please read it and pass on. In the last few years I’ve had SIX messages from people who saved a kid’s life after clicking on the link from my feed.
slate.com/technology/2...
Unbelievably honoured to read Tatiana Engel's (@engeltatiana.bsky.social) wonderfully written Preview on our work "Linking neural manifolds to circtuit structure in recurrent networks" (with @lpezon.bsky.social & @gerstnerlab.bsky.social) in this issue of Neuron
www.cell.com/neuron/fullt...
🙏
1/7 New paper accepted as ICML spotlight arxiv.org/abs/2605.03517! We unify self-supervised learning (SSL) algorithms (e.g., contrastive, VICReg, stopgrad) via latent distribution matching (LDM), which matches an induced latent distribution to an explicit latent model.
Belated update: I joined UIUC ECE as an Assistant Professor. Our lab works at the intersection of theoretical neuroscience, machine learning, and dynamical systems, with a focus on learning and spiking networks. I had to miss #COSYNE2026 for visa reasons. 1/2
I am looking for a theory/computational POSTDOC position in EU or east coast US. I am interested in how learning and plasticity shape population dynamics & representational geometries & how these changes are reflected in behavior.
If you are at #COSYNE2026 & interested, hit me up in Whova, not here
