We are pleased to announce the ‘Swiss Equivariant Machine Learning Workshop’ at CECAM, Lausanne, 11th to 14th of July 2022.

Sign up: https://sites.google.com/mit.edu/swiss-equivariant-learning
Registration Deadline: June 24th

Machine learning (ML) based atomistic models are often faced with the challenge of learning physical or chemical properties that have well-defined transformations (equivariance) under translation, rotation, and reflections of the corresponding atomic structures. The last few years have seen significant progress on enhancing ML approaches by including symmetry preserving operations, which has led to noteworthy improvements in both the accuracy and data-efficiency of models predicting physical quantities.

In this 4-day workshop we will explore various aspects of this exciting field including the prediction of tensorial quantities, generative models, theoretical aspects, machine learning interaction potentials and many others.  There will be hands-on tutorials as well as discussions and we particularly encourage the participation of junior researchers.

To sign up, please visit our website
https://sites.google.com/mit.edu/swiss-equivariant-learning
space is limited so to guarantee a place sign up early!

Hope to see you in July!

Confirmed speakers:
Ivan Diaz (Bern Hospital)
Boris Kozinsky (Harvard University)
lyes Batatia (University of Cambridge)
Michele Ceriotti (EPFL)
Kristof Schuett (Technische Universität Berlin)
Francesco Cagnetta (EPFL)
Guillaume Fraux (EPFL)
Maurice Weiler
Taco Cohen (Qualcomm)

Organising committee:
Simon Batzner and Albert Musaelian (Harvard)
Mario Geiger and Tess Smidt (MIT)
Josh Rackers and Thomas Hardin (Sandia National Labs)
Jigyasa Nigam and Martin Uhrin (EPFL)