GastroPy is now out in early beta! Please to share our Python toolbox for electrogastrography and stomach-brain coupling analyses. It includes tools for cleaning, visualising, and analysing EGG data, plus fMRI stomach-brain coupling workflows. Docs, code, and preprint below. osf.io/preprints/ps...

And another publication from our A04 project!

This time, Milena Pertz and colleagues investigated empathy for different pain modalities! 🤷‍♀️

Read it here: doi.org/10.1016/j.jp...

The stinker - inofficial mascot of the Ig Nobel prizes

Ig Nobel Euro Show 2026
Save the date! April, 17th 2026, 7 pm +++ Further details follow soon

Marc Abrahams and a line-up of Ig Nobel prize winners will present their research at the University of Duisburg-Essen (@unidue.bsky.social) in Essen, Germany, free admission
special guest: Minkorrekt!

Researchers reveal bias in a widely used measure of algorithm performance When scientists test algorithms that sort or classify data they often turn to a trusted tool called Normalized Mutual Information (or NMI) to measure how well an algorithm’s output matches reality. Bu...

A new study co-authored by SFI’s Mark Newman and Max Jerdee shows that a widely used metric for evaluating algorithms (NMI) can produce biased results, impacting scientific conclusions.

To address this, the authors developed an asymmetric, reduced version of the mutual information metric.

What a week!
Congrats to the whole SFB1280 team, especially our speakers Onur Güntürkün and Dagmar Timmann. Also huge thanks to Sigrid Elsenbruch who led „team translation“. Of course I am convinced that this was crucially important to secure the 3rd funding period.

Programmable wave-based analog computing machine: a metastructure that designs metastructures - Nature Communications This study introduces and validates a reconfigurable metastructure that uses electromagnetic waves to perform analog complex-valued mathematical computations. This device executes both stationary and ...

Electromagnetic waves enable low-energy, parallel computation. Your brain has them. If humans can figure this out, 4 billion years of evolution could too.

Programmable wave-based analog computing machine: a metastructure that designs metastructures
www.nature.com/articles/s41...
#neuroscience

We now have a CRC-specific starter pack! ✨

Let me know if you are a member and would like to be added! ⤵️

The first computational neuroscience of pain conference is coming to Aarhus! Sign up now. Awesome line up. @francescafardo.bsky.social @torwager.bsky.social @christianbuchel.bsky.social and more!

38M! 🎉

Join us at #NeurIPS2025 for our Data on the Brain & Mind workshop! We aim to connect machine learning researchers and neuroscientists/cognitive scientists, with a focus on emerging datasets.

More info: data-brain-mind.github.io

Neural models for detection and classification of brain states and transitions - Communications Biology A deep learning self-supervised hybrid CNN-autoencoder model is used to detect brain states and transitions, like wakefulness, slow oscillations and microarousals, during the emergence from anesthesia...

Neural models for detection and classification of brain states and transitions
www.nature.com/articles/s42...
#neuroscience

🚨 New paper out in GigaScience!
To avoid common pitfalls in multivariate modeling: combine external validation with pre-registration — freeze your model before testing.

For the pros: decide on the fly when to stop training!
First-authored by the brilliant @ggallitto.bsky.social

➡️New paper out with ELH members Balint Kincses and Ulrike Bingel: "External validation of machine learning models-registered models and adaptive sample splitting". 🍾

pubmed.ncbi.nlm.nih.gov/40366867/

External validation of machine learning models—registered models and adaptive sample splitting

Our new manuscript discussing pre-registration of predictive modelling studies and the importance of external validations is out now, published in GigaScience.

Give a look at it here:

doi.org/10.1093/giga...

#machinelearning #neuroscience #neuroimaging #bioinformatics

scikit-learn Version 1.6.0 Release Highlights YouTube video by scikit-learn

❄️ The Christmas release is here! ❄️

Introducing scikit-learn 1.6 with:

🟢 2 major features & 34 improvements
🔵 5 efficiency boosts & 21 enhancements
🟡 14 API changes
🔴 30 fixes
👥 160 amazing contributors

youtu.be/7wiHChpwJe8

OHBM has confirmed that Dec 17 is a hard deadline for abstracts.

Version 1.6 Legend for changelogs something big that you couldn’t do before., something that you couldn’t do before., an existing feature now may not require as much computation or memory., a miscellaneous min...

Please help us test the first release candidate for scikit-learn 1.6: pip install scikit-learn==1.6.0rc1

Changelog: scikit-learn.org/1.6/whats_ne...

In particular, if you maintain a project with a dependency on
scikit-learn, please let us know about any regression.

We are proud of this piece related to our science communication project! 🤩

We present a teaching and learning concept addressing placebo and nocebo effects in competency-based communication training👩‍⚕️

The paper: pubmed.ncbi.nlm.nih.gov/39415814/
The project: treatment-expectation.de/projekte-peo...

All - Bluesky Directory A curated collection of all things relating to the Blue Sky social media platform.

To find all Starter Packs go here:
blueskydirectory.com/starter-pack...

Are you a neuroscientist interested in sustainability, but don't know who to follow? 🤔

You're in luck! Here's a starter pack of neuroscientists who post about climate, and researchers who work in the intersection of neuro/psych and climate change!

🌱Msg if you want to be added!

go.bsky.app/E1iW12T

Welcome @nilearn.bsky.social to Bluesky! Nilearn is an amazing package for neuroimaging analysis in Python - certainly one of the most heavily used packages in our lab.

A starter pack of layer-fMRI folks here: go.bsky.app/TUWFNzg

I would like to be added too 😁

Made a new starter pack with folks who use brain-based predictive models in their analyses!

Let me know if you'd like to be added. 🧠🤖📋

go.bsky.app/BDv5bd3

Adaptive Intelligence: leveraging insights from adaptive behavior in animals to build flexible AI systems Biological intelligence is inherently adaptive -- animals continually adjust their actions based on environmental feedback. However, creating adaptive artificial intelligence (AI) remains a major chal...

Adaptive Intelligence: leveraging insights from adaptive behavior in animals to build flexible AI systems - this looks like a fun paper by @trackingactions.bsky.social, related to a great talk she recently gave at Stanford. looking forward to reading it!

My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.

fleuret.org/dlc/

And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)

fleuret.org/lbdl/

Scikit-learn is on bluesky 🧡💙

For the Blueskyers interested in #NeuroAI 🧠🤖,
I created a starter pack! Please comment on this if you are not on the list and working in this field 🙂

go.bsky.app/CscFTAr

Predictive learning shapes the representational geometry of the human brain - Nature Communications This study shows that the human brain aligns its neural representations to the statistical structure of sensory inputs, and that the magnitude of this representational shift correlates with the synerg...

🔵 New Paper 🔵

Happy to announce that our paper linking predictive learning and representational geometry in the human 🧠 is out today in #NatureComms!

with @drjuliamoser.bsky.social, Hubert Preissl and Markus Siegel

📜👉 nature.com/articles/s41467-024-54032-4

If you have the feeling that @bsky.app is different, maybe you are right.

The current migration is breaking the typical rich-get-richer effect wrt other platforms #scaling

Data:

Twitter: 10.9M users
BlueSky (Mar 2024): 4.1M users, 🙏 @andreajpg.bsky.social
Mastodon: 3.8M users, 🙏 @tiago.skewed.de