Sign in

Flavio Martinelli

@flavioh.bsky.social
225 followers 220 following 33 posts

I like brains 🧟‍♂️ 🧠 PhD student in computational neuroscience supervised by Wulfram Gerstner and Johanni Brea flavio-martinelli.github.io

PostsRepliesMedia
Reposted by Flavio Martinelli
Alireza Modirshanechi @modirshanechi.bsky.social · 15/08/2026
Excited to share that I'll be starting as a junior professor and Emmy Noether awardee at the University of Göttingen this October! 🥳 🚀 I'll be hiring #phd students and #postdoc across #machinelearning, #neuroscience and #cogsci: modirlab.github.io/open-positio... Please spread the word! 🙏
PhD ad informationPostdoc ad informationInformation about Göttingen and equal opportunities
1217059
Reposted by Flavio Martinelli
Satpreet (Sat) Singh @satpreetsingh.bsky.social · 29/07/2026
How do you "see" with electric eyes? How does collective behavior emerge from individual interactions? Nocturnal weakly electric fish evolved to do this, but studying naturalistic social behavior is very hard. Our solution? Virtual 'fish' 🤖🐟⚡ 📄 arxiv.org/abs/2511.08436
17925
Reposted by Flavio Martinelli
Louis Pezon @lpezon.bsky.social · 30/06/2026
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...
biorxiv.org
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...
16425
Reposted by Flavio Martinelli
GerstnerLab @gerstnerlab.bsky.social · 29/06/2026
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.
12612
Reposted by Flavio Martinelli
Fatih Dinc @fatihdinc.bsky.social · 23/06/2026
Why did RNNs fail to learn long-term dependencies? What if we added one more modification, maybe now? It turns out we can give a pretty broad, analytical answer! See the attached paper for a rigorous treatment using centre manifolds, low-rank RNNs, and dynamical systems theory! go.aps.org/4fXWEeF
go.aps.org
Ghost Mechanism: An Analytical Model of Abrupt Learning in Recurrent Networks
This study establishes the ghost mechanism as an underlying mechanism for abrupt learning, whereby the recurrent neural network develops ghost points---transient dynamical bottlenecks---and identifies...
03510
Reposted by Flavio Martinelli
Zihan Wu @zihan-wu.bsky.social · 16/06/2026
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
3339
Reposted by Flavio Martinelli
Dr Nick @nmwilkinson.eurosky.social · 11/06/2026
This is cool and makes a lot of sense. Reminds me of the theory of neutral networks in evolutionary theory, where networks of neutral genotype changes enable populations to traverse the fitness landscape without getting stuck in local minima
176
Reposted by Flavio Martinelli
GerstnerLab @gerstnerlab.bsky.social · 10/06/2026
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
0135
Flavio Martinelli @flavioh.bsky.social · 10/06/2026
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
519953
Reposted by Flavio Martinelli
Kempner Institute at Harvard University @kempnerinstitute.bsky.social · 03/02/2026
🤖📊 NEW in the Deeper Learning blog: @annhuang42.bsky.social & @kanakarajanphd.bsky.social break down their recent work examining how #RNNs solve the same task in different ways, and why that matters. Joint work with @satpreetsingh.bsky.social & @flavioh.bsky.social bit.ly/4kj4fVd #NeuroAI
bit.ly
Measuring and Controlling Solution Degeneracy Across Task-Trained Recurrent Neural Networks - Kempner Institute
Despite reaching equal performance success when trained on the same task, artificial neural networks can develop dramatically different internal solutions, much like different students solving the sam...
0266
Flavio Martinelli @flavioh.bsky.social · 04/12/2025
🧵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 🤯
2146
Reposted by Flavio Martinelli
Ann Huang @annhuang42.bsky.social · 24/11/2025
📍Excited to share that our paper was selected as a Spotlight at #NeurIPS2025! arxiv.org/pdf/2410.03972 It started from a question I kept running into: When do RNNs trained on the same task converge/diverge in their solutions? 🧵⬇️
510927
Reposted by Flavio Martinelli
Greg Jefferis @jefferis.bsky.social · 05/10/2025
Exciting news for #drosophila #connectomics and #neuroscience enthusiasts: the Drosophila male central nervous system connectome is now live for exploration. Find out more at the landing page hosted by our Janelia FlyEM collaborators www.janelia.org/project-team....
janelia.org
Male CNS Connectome
A team of researchers has unveiled the complete connectome of a male fruit fly central nervous system —a seamless map of all the neurons in the brain and nerve cord of a single male fruit fly and the ...
214569
Reposted by Flavio Martinelli
GerstnerLab @gerstnerlab.bsky.social · 30/09/2025
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
193
Reposted by Flavio Martinelli
Guillaume Bellec @bellecguill.bsky.social · 23/05/2025
To our fellow researchers at Harvard and elsewhere. 🧪🧠 I have funds for visiting PhDs or postdocs at TU in Vienna. For short stay or full PhD email me. For professors, check for instance, this tenure track opening or ask in private for options informatics.tuwien.ac.at/news/2909
0113