Machine Learning in Science
We build probabilistic #MachineLearning and #AI Tools for scientific discovery, especially in Neuroscience. Probably not posted by @jakhmack.bsky.social.
📍 @ml4science.bsky.social, Tübingen, Germany
- I’m super excited to present our new work in #Eurips2025 and #Neurips2025! We developed FNOPE: a new simulation-based inference (SBI) method which excels at inferring function-valued parameters! Paper: openreview.net/forum?id=yB5... Code: github.com/mackelab/fnope (1/9)
- On our blog: For decades, brain simulations have either been largely simplified, or they could not perform cognitive tasks. #JAXLEY, a new AI tool, opens possibilities to build brain simulations that overcome both limitations: www.machinelearningforscience.de/en/jaxley-ai... #AIforScience
- From hackathon to release: sbi v0.25 is here! 🎉 What happens when dozens of SBI researchers and practitioners collaborate for a week? New inference methods, new documentation, lots of new embedding networks, a bridge to pyro and a bridge between flow matching and score-based methods 🤯 1/7 🧵
- Natural light, open spaces and room for collaboration — here’s a preview of our new home for AI research in Tübingen. We can’t wait to move in! @unituebingen.bsky.social @maxplanckcampus.bsky.social @mwk-bw.bsky.social #MovingForward #BehindTheScenes #NewBuilding #TUEAI
- [Not loaded yet]
- The neurons that encode sequential information into working memory do not fire in that same order during recall, a finding that is at odds with a long-standing theory. Read more in this month’s Null and Noteworthy. By @ldattaro.bsky.social #neuroskyence www.thetransmitter.org/null-and-not...
- Have I been to Antarctica? No. But my colleagues have, and we can learn a lot from the data they collected! Really happy to share that our work is now published!
- Thrilled to share that our paper on using simulation-based inference for inferring ice accumulation and melting rates for Antarctic ice shelves is now published in Journal of Glaciology! www.cambridge.org/core/journal...
- [Not loaded yet]
- [Not loaded yet]
- Great news! Our March SBI hackathon in Tübingen was a huge success, with 40+ participants (30 onsite!). Expect significant updates soon: awesome new features & a revamped documentation you'll love! Huge thanks to our amazing SBI community! Release details coming soon. 🥁 🎉
- Thanks so much for the shout-out, and congrats on your exciting work!! 🎉 🙂 Also, a good reminder to share that our work is now out in Cell Reports 🙏🎊 ⬇️ www.cell.com/cell-reports...
- [Not loaded yet]
- [Not loaded yet]
- Exciting new paper out of a Tübingen-Bonn collaboration, with three researchers from our cluster involved: first author @stefanieliebe.bsky.social, @matthijspals.bsky.social & @mackelab.bsky.social. Congrats to the team!
- Science Alert 🚨: Our paper is now out in @natureneuro.bsky.social - We show that the firing phase of neurons in human MTL doesn’t reflect the order of events, challenging a long-standing theory of human memory. nature.com/articles/s41593-025-01893-7
- Science Alert 🚨: Our paper is now out in @natureneuro.bsky.social - We show that the firing phase of neurons in human MTL doesn’t reflect the order of events, challenging a long-standing theory of human memory. nature.com/articles/s41593-025-01893-7
- Together with @dendritesgr.bsky.social, we’ll be hosting a tutorial on constructing and optimizing biophysical models (via Jaxley & DendroTweaks) 🚀 Join us in Florence if you like dendrites, biophysics, or optimization!
- 1) Some exciting science in turbulent times: How do mice distinguish self-generated vs. object-generated looming stimuli? Our new study combines VR and neural recordings from superior colliculus (SC) 🧠🐭 to explore this question. Check out our preprint doi.org/10.1101/2024... 🧵
- Happy to share my second paper with Peter Dayan on our decision-theoretic approach to perceptual multistability (see the tweeprint of the first paper here x.com/neuroprincip...). Paper: A decision-theoretic model of multistability biorxiv.org/content/10.1...
- @vetterj.bsky.social and I are excited to present our work at #NeurIPS2024! We present Sourcerer: a maximum-entropy, sample-based solution to source distribution estimation. Paper: openreview.net/forum?id=0cg... Code: github.com/mackelab/sou... (1/8)
- How to find all fixed points in piece-wise linear recurrent neural networks (RNNs)? A short thread 🧵 In RNNs with N units with ReLU(x-b) activations the phase space is partioned in 2^N regions by hyperplanes at x=b 1/7
-
View full threadBut not all of the 2^N regions do! Each neuron partitions the R-dim subspace of dynamics with a hyperplane (here a line). N hyperplanes can partition R-dim space into at most O(N^R) regions. We can thus reduce our search space by only solving for fixed points in these! 6/7
- We reduce the cost of finding all fixed-points in piece-wise linear low-rank RNNs from 2^N to O(N^R)! This is part of our recent NeurIPS paper, presented tomorrow: bsky.app/profile/mack... Special thanks to Manuel Gloeckler for helping write out a proof! 7/7
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- Watching the sbi-toolbox grow up, seeing its many uses on a wide range of applications, and experiencing the growth, momentum + team-spirit of the sbi community has been amazing. We now have a short software paper with many new contributions and contributors! So many thanks, and get involved!
- The sbi package is growing into a community project 🌍 To reflect this and the many algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper 📝 Check it out, and reach out if you want to get involved: arxiv.org/abs/2411.17337
- The sbi package is growing into a community project 🌍 To reflect this and the many algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper 📝 Check it out, and reach out if you want to get involved: arxiv.org/abs/2411.17337
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
