Our paper "Rarely categorical, highly separable representations along the cortical hierarchy" is now out in Nature! www.nature.com/articles/s41... In this paper, we studied whether the brain is well-organized and interpretable, both globally and locally. (See thread below.)

Both brains and RNNs can re-use components of computation across similar tasks or contexts. But what exactly are those “shared components”? How can they be used to solve several tasks? We address these questions in a new preprint with @avm.bsky.social! Link: www.biorxiv.org/content/10.6...

Interpretable compositional computation with recurrent neural networks

Flexible cognition utilizes reusable components to enable rapid adaptation of behavior to different contexts or tasks. Analysis of artificial neural networks trained on multiple tasks suggested that t...

biorxiv.org

How can the brain learn the hidden hierarchical structure from high dimensional data? In our latest work, we use synthetic datasets to analyze two classes of bio-plausible learning rules: variants of Direct Feedback Alignment, and local self-supervised learning. We find only the latter succeeds.

📂 We're sharing code of a classic from the lab! A biologically inspired RL model from Frémaux, Sprekeler @sprekeler.bsky.social & Gerstner (2013, PLOS CB): a continuous-time actor–critic using spiking neurons that learn to navigate a water maze

Accepted at ICML 2026. I am extremely proud of this work. Local learning is starting to work really well! The theoretical perspective of local learning minimizing an emergent global objective has been eye opening Congrats @zihan-wu.bsky.social and Ariane Delrocq! Great team

Zihan Wu@zihan-wu.bsky.social · 2mo ago

Can we match self-supervised backpropagation using local learning rules? We show it is possible in our new paper accepted by ICML. We achieve: 1. theoretical equivalence to BP in a controlled setup 2. new SOTA for local learning across image datasets 3. same performance as BP on multiple datasets

How far are biologically-plausible local learning rules from backpropagation (BP)? In our new ICML paper we look at local self-supervised learning and find how to better align its gradients to BP. We achieve competitive performance on various datasets!

Zihan Wu@zihan-wu.bsky.social · 2mo ago

Can we match self-supervised backpropagation using local learning rules? We show it is possible in our new paper accepted by ICML. We achieve: 1. theoretical equivalence to BP in a controlled setup 2. new SOTA for local learning across image datasets 3. same performance as BP on multiple datasets

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

Flavio Martinelli@flavioh.bsky.social · 2mo ago

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

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...

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... 🙏

Finding clues to circuit structure in population dynamics and single-neuron selectivity

In this issue of Neuron, Pezon et al. introduce neural circuit models with flexible connectivity structure that can generate low-dimensional population dynamics with different distributions of single-...

cell.com

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?

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...

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.

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...

Linking neural manifolds to circuit structure in recurrent networks

Dimensionality reduction methods are widely used in neuroscience to investigate two complementary aspects of neural activity: the distribution of sing…

sciencedirect.com

🧵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 🤯

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. 🤯

David G. Clark@david-g-clark.bsky.social · 9mo ago

Now in PRX: Theory linking connectivity structure to collective activity in nonlinear RNNs! For neuro fans: conn. structure can be invisible in single neurons but shape pop. activity For low-rank RNN fans: a theory of rank=O(N) For physics fans: fluctuations around DMFT saddle⇒dimension of activity

Lab members are at the Bernstein conference @bernsteinneuro.bsky.social with 9 posters! Here’s the list: TUESDAY 16:30 – 18:00 P1 62 “Measuring and controlling solution degeneracy across task-trained recurrent neural networks” by @flavioh.bsky.social

New in @pnas.org: doi.org/10.1073/pnas... We study how humans explore a 61-state environment with a stochastic region that mimics a “noisy-TV.” Results: Participants keep exploring the stochastic part even when it’s unhelpful, and novelty-seeking best explains this behavior. #cogsci #neuroskyence

🎉 "High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model" will be presented as an oral at #NeurIPS2025 🎉 Feeling very grateful that reviewers and chairs appreciated concise mathematical explanations, in this age of big models. www.biorxiv.org/content/10.1... 1/2

🧠 “You never forget how to ride a bike”, but how is that possible? Our study proposes a bio-plausible meta-plasticity rule that shapes synapses over time, enabling selective recall based on context

Context selectivity with dynamic availability enables lifelong continual learning

“You never forget how to ride a bike”, – but how is that possible? The brain is able to learn complex skills, stop the practice for years, learn other…

sciencedirect.com

So happy to see this work out! 🥳 Huge thanks to our two amazing reviewers who pushed us to make the paper much stronger. A truly joyful collaboration with @lucasgruaz.bsky.social, @sobeckerneuro.bsky.social, and Johanni Brea! 🥰 Tweeprint on an earlier version: bsky.app/profile/modi... 🧠🧪👩‍🔬

Open Mind@openmindjournal.bsky.social · 12mo ago

Attending #CCN2025? Come by our poster in the afternoon (4th floor, Poster 72) to talk about the sense of control, empowerment, and agency. 🧠🤖 We propose a unifying formulation of the sense of control and use it to empirically characterize the human subjective sense of control. 🧑‍🔬🧪🔬

Is it possible to go from spikes to rates without averaging? We show how to exactly map recurrent spiking networks into recurrent rate networks, with the same number of neurons. No temporal or spatial averaging needed! Presented at Gatsby Neural Dynamics Workshop, London.

From Spikes To Rates

YouTube video by Gerstner Lab

youtu.be

Excited to present at the PIMBAA workshop at #RLDM2025 tomorrow! We study curiosity using intrinsically motivated RL agents and developed an algorithm to generate diverse, targeted environments for comparing curiosity drives. Preprint (accepted but not yet published): osf.io/preprints/ps...

Stoked to be at RLDM! Curious how novelty and exploration are impacted by generalization across similar stimuli? Then don't miss my flash talk in the PIMBAA workshop (tmr at 10:30, E McNabb Theatre) or stop by my poster tmr (#74)! Looking forward to chat 🤩 www.biorxiv.org/content/10.1...

Representational similarity modulates neural and behavioral signatures of novelty

Novelty signals in the brain modulate learning and drive exploratory behaviors in humans and animals. While the perceived novelty of a stimulus is known to depend on previous experience, the effect of...

biorxiv.org

Our new preprint 👀

Matteo Carandini@carandinilab.net · last yr.

The firing of neural populations is high-dim even if their subthreshold activity is low-dim! This work by @bio-emergent.bsky.social and @haydari.bsky.social shows how, with a solvable model, a data analysis technique, and data from mouse visual cortex: www.biorxiv.org/content/10.1...

Interested in high-dim chaotic networks? Ever wondered about the structure of their state space? @jakobstubenrauch.bsky.social has answers - from a separation of fixed points and dynamics onto distinct shells to a shared lower-dim manifold and linear prediction of dynamics.

Jakob Stubenrauch@jakobstubenrauch.bsky.social · last yr.

(1/3) How to analyse a dynamical system? Find its fixed points, study their properties! How to analyse a *high-dimensional* dynamical system? Find its fixed points, study their properties! We do that for a chaotic neural network! finally published: doi.org/10.1103/Phys...

Episode #22 in #TheoreticalNeurosciencePodcast: On 50 years with the Hopfield network model - with Wulfram Gerstner theoreticalneuroscience.no/thn22 John Hopfield received the 2024 Physics Nobel prize for his model published in 1982. What is the model all about? @icepfl.bsky.social

A cool EPFL News article was written about our recent neurotheory paper on spikes vs rates! Super engaging text by science communicater Nik Papageorgiou. actu.epfl.ch/news/brain-m... Definitely more accessible than the original physics-style, 4.5-page letter 🤓 journals.aps.org/prl/abstract...

Brain models draw closer to real-life neurons

Researchers at EPFL have shown how rough, biological spiking neural networks can mimic the behavior of brain models called recurrent neural networks. The findings challenge traditional assumptions and...

actu.epfl.ch

Super excited to see my PhD thesis featured by EPFL! 🎓 actu.epfl.ch/news/learnin... P.S.: There's even a French version of the article! It feels so fancy! 😎 👨‍🎨 🇫🇷 actu.epfl.ch/news/apprend...

Learning from the unexpected

A researcher at EPFL working at the crossroads of neuroscience and computational science has developed an algorithm that can predict how surprise and novelty affect behavior.

actu.epfl.ch

New round of spike vs rate? The concentration of measure phenomenon can explain the emergence of rate-based dynamics in networks of spiking neurons, even when no two neurons are the same. This is what's shown in the last paper of my PhD, out today in Physical Review Letters 🎉 tinyurl.com/4rprwrw5