Understanding ML with Statistical Physics – Lenka Zdeborová [online]

Youtube stream: https://youtu.be/yd09g0RaqLg

After the success of previous sessions, we would like to invite you to the next online meetup! This time, we have another outstanding speaker, Lenka Zdeborová, who will share how to make use of statistical physics in machine learning!

Abstract:
The affinity between statistical physics and machine learning has a long history; this is reflected even in the machine learning terminology that is in part adopted from physics. I will describe the main lines of this long-lasting friendship in the context of current theoretical challenges and open questions about deep learning. Theoretical physics often proceeds in terms of solvable synthetic models, and I will describe the related line of work on solvable models of simple feed-forward neural networks.

Bio:
Lenka is a researcher CNRS (Centre national de la recherche scientifique) in the IPhT (Institut de Physique Theorique) at Saclay, France, since 2010. She has backround in the statistical physics and its applications in computer science and technology.

https://www.linkedin.com/in/lenka-zdeborova-4895ba4/
http://artax.karlin.mff.cuni.cz/~zdebl9am/