Sign in

Matteo Saponati

@matteosaponati.bsky.social
227 followers 86 following 15 posts

I am a research scientist in Machine Learning and Neuroscience. I am fascinated by life and intelligence, and I like to study complex systems. I love to play music and dance. Postdoctoral Research Scientist @ ETH Zürich ↳ matteosaponati.github.io

PostsRepliesMedia
Matteo Saponati @matteosaponati.bsky.social · 16/04/2025
Take our short 5-min anonymous survey on the Neuromorphic field’s current state & future: 📋 tinyurl.com/3jkszrnr 🗓️ Open until May 12, 2025 Results will be shared openly and submitted for publication. Your input will help us understand how interdisciplinary trends are shaping the field.
tinyurl.com
Neuromorphic Questionnaire
This form collects valuable information from the Neuromorphic Community as part of a project led by Matteo Saponati, Laura Kriener, Sebastian Billaudelle, Filippo Moro, and Melika Payvand. The goal is...
1810
Reposted by Matteo Saponati
Jérôme Lecoq @jeromelecoq.bsky.social · 15/04/2025
How does our brain predict the future? Our review of predictive processing + research program is now on arXiv arxiv.org/abs/2504.09614 50+ neuroscientists distributed across the world worked together to create this unique community project.
28631
Reposted by Matteo Saponati
Elisa Donati @elisadonati.bsky.social · 02/04/2025
🌟 Paper out in npj Unconventional Computing! www.nature.com/articles/s44... A system built with just a few neurons, yet able to solve a complex task — not by stacking layers or going deeper, but by embracing unconventional thinking. This is neuromorphic to me!
nature.com
A neuromorphic multi-scale approach for real-time heart rate and state detection - npj Unconventional Computing
npj Unconventional Computing - A neuromorphic multi-scale approach for real-time heart rate and state detection
1145
Reposted by Matteo Saponati
Giacomo Indiveri @giacomoi.bsky.social · 02/04/2025
I'm extremely proud of this work, which shows how using the physics of analog electronic circuits helps us understand learning and computational principles of cortical neural networks and build efficient neural processing systems that can complement and outperform AI accelerators in edge computing!
194
Matteo Saponati @matteosaponati.bsky.social · 18/02/2025
1/ I am very excited to announce that our paper "The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training" is available on arXiv 💜 arxiv.org/abs/2502.10927 How is information encoded in self-attention matrices?How to interpret it? ⬇️
arxiv.org
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
Self-attention is essential to Transformer architectures, yet how information is embedded in the self-attention matrices and how different objective functions impact this process remains unclear. We p...
183
Matteo Saponati @matteosaponati.bsky.social · 23/01/2025
hey Bluesky world, I realized I didn't post anything here yet I'll start with sharing a recent blog post on the workshop we organised at the last Bernstein Conference 2024. I hope you enjoy it 💃 Thank you @melikapayvand.bsky.social , Laura, and Ana for the feedback and suggestions 💜
matteosaponati.github.io
It’s been a while since I last published something on my personal blog. Life has moved along in beautiful, unexpected ways, and I’ve experienced many absolutely lovely moments. On the professional side, I recently had the opportunity to organize a workshop at the Bernstein Conference in Frankfurt am Main (my lovely and chaotic Frankfurt <3). This workshop was brought to life thanks to the other incredible organizers, Laura Kriener and Melika Payvand, with their creativity, initiative, and vision. I feel grateful to be a part of this vibrant community. So, why not use this opportunity to write here again?
0152