The Laboratory of Computational Neuroscience @EPFL studies models of neurons, networks of neurons, synaptic plasticity, and learning in the brain.
GerstnerLab
Ever heard of the lottery ticket hypothesis?
Our new paper shows that lottery tickets are not a useful metaphor to explain the success of overparameterized neural networks - and suggests an alternative metaphor: escape dimensions
Novelty is not just about whats new, but also what feels new given past experience. New study from Sophia Becker in Wulfram Gerstner’s @epfl-brainmind.bsky.social lab posits a model showing how similarity between familiar and novel stimuli shapes exploration and learning - doi.org/10.1016/j.ne...
Incredibly grateful to @cmiehl.bsky.social and @gjorjulijana.bsky.social for their thoughtful and spot-on Preview "Novelty beyond counting" of our recent work in Neuron with @modirshanechi.bsky.social and @gerstnerlab.bsky.social! 🧠✨ It's a real honor 🙏 www.cell.com/neuron/fullt...
Excited to share our new paper to be published in Neuron!
With Valentin Schmutz @bio-emergent.bsky.social and Wulfram Gerstner @gerstnerlab.bsky.social, we explore how circuit structure in RNNs shapes network computation and single-neuron responses.
www.sciencedirect.com/science/arti...
Episode #39 in #TheoreticalNeurosciencePodcast:
On modeling neural population activity with mean-field models – with Tilo Schwalger
theoreticalneuroscience.no/thn39
How can mean‑field models be systematically derived from the underlying microscopic dynamics of individual neurons?
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...
🙏
Presenting a poster tomorrow at Cosyne 26:
[3-033] Compositional computation via shared latent dynamics in low-rank RNNs.
With @avm.bsky.social, we explore how RNNs can re-use the same dynamics across different tasks, and what it implies for their connectivity and neural activity.
This was a lot of fun! From my side, it started with a technical Q: what's the relation between two-side cavity and path integrals? Turns out it's a fluctuation correction - and amazingly, this also enable the "O(N) rank" theory by @david-g-clark.bsky.social and @omarschall.bsky.social. 🤯
🧵Excited to present our latest work at #Neurips25! Together with @avm.bsky.social, we discover 𝐜𝐡𝐚𝐧𝐧𝐞𝐥𝐬 𝐭𝐨 𝐢𝐧𝐟𝐢𝐧𝐢𝐭𝐲: regions in neural networks loss landscapes where parameters diverge to infinity (in regression settings!)
We find that MLPs in these channels can take derivatives and compute GLUs 🤯
GerstnerLab
EPFL Brain Mind Institute
Sophia Becker
Gaute Einevoll
Valentin Schmutz
Louis Pezon
Louis Pezon
Dimensionality reduction methods are widely used in neuroscience to investigate two complementary aspects of neural activity: the distribution of sing…
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
