π¨ #CCN2026 Proceedings submissions are open!
CCN 2026 again features an 8-page Proceedings track (alongside extended abstracts). Accepted papers will appear in CCN-Proceedings (CCNβP) with DOIs on OpenReview.
@stefsm.bsky.social
Assistant Professor Chalmers and GΓΆteborg University π± ML + CogSci + StatPhys π stefsmlab.github.io π
π¨ #CCN2026 Proceedings submissions are open!
CCN 2026 again features an 8-page Proceedings track (alongside extended abstracts). Accepted papers will appear in CCN-Proceedings (CCNβP) with DOIs on OpenReview.
It is a great pleasure to host the Workshop in Advancements in High-Dimensional Methods for Machine Learning next week at Chalmers/GU!
We have a great set of speakers, and I look forward to the talks and discussions!
π chalmers.se/en/current/c...
Our paper just came out in PRX!
Congrats to Nishil Patel and the rest of the team*
TL;DR: We analyse policy learning through the lens of statphys, revealing distinct scaling regimes with sharp transitions.
π journals.aps.org/prx/abstract...
*Seb Lee @sebgoldt.bsky.social @saxelab.bsky.social
The first poster is actually #460, but I am actually still queueing at the registration.
First memorable experience of this ICLR is the longest queue of my life. π
Here at #ICLR2025 and it's going to be a busy week!
1. Today at 10am, Optimal Protocols for Continual Learning via Statistical Physics and Control Theory, Poster #342
2. Tomorrow at 10am, A Theory of Initialisation's Impact on Specialisation Poster, #342
3. Speaking at the SCSLWorkshop on Monday.
Less than 10 days to apply to the last edition of the Analytical Connectionism summer school!
Deadline: April 18th π¨
Apply here www.analytical-connectionism.net/school/2025/
Where? London, UK. When? Aug 25-Sep 5.
I really enjoyed working on this. What started as a reproducibility issue ended up revealing a more complex picture of mean-field dynamics than I originally thought, making me rethink the specialisation phenomenon.
Soon at @iclr-conf.bsky.social!
π openreview.net/forum?id=RQz...
Excited to meet for the first time and exchange ideas with fellow Nordic statistical physicists next week @NorditaSweden
Workshop on StatPhys!
I'll be presenting our research on ML bias through the lens of disordered systems.
π indico.fysik.su.se/event/8942/
and @sainsburywellcome.bsky.social π
05.02.2025 20:56 β π 1 π 0 π¬ 0 π 0Special thanks to our speakers: Remi Monasson, Tim Rogers, Tali Sharot, Merav Ahissar, Xuechunzi Bai, Marco Baity-Jesi, Mathew Diamond, Lasana Harris, Tiago Maia, Angela Radulescu, Levent Sagun, and Fanny Yang.
And sponsors: @gatsbyucl.bsky.social and @neuroinformatics.dev
Happy to announce that the Analytical Connectionism summer school is back!
This year we'll dive into "bias" across ML, Neuroscience, and Psychology.
π Aug 25-Sep 5
πΊοΈ London, UK
π www.analytical-connectionism.net/school/2025/
Applications are open!
ML methods are an asset in analysing numerically glassy dynamics - a notoriously difficult physics problem. If you want to know more on recent results and future directions, check out our "Roadmap on machine learning glassy dynamics", just appeared on Nature Reviews www.nature.com/articles/s42...
06.01.2025 09:16 β π 9 π 2 π¬ 0 π 1Looking for a PhD in Cognitive Science, Cognitive Neuroscience or related in Germany? One week left to apply for the Max Planck School of Cognition: cognition.maxplanckschools.org/en/application
#PsychSciSky #compneurosky #neuroskyence #NeuroAI #Neuroimaging
First post on π¦!
Next week, Iβll speak about Curriculum Learning at the workshop "At the Crossroads of AI and Cognitive Science". Join me if you are in the area! π www.chalmers.se/en/current/c...