Seminar by Bronstein “Geometric deep learning: from Euclid to drug design”

Michael Bronstein (University of Oxford) will present a seminar on August 17th, from 10:15 to 11:15 at the IMP Lecture hall at Campus-Vienna-Biocenter 1, 1030 Vienna.

Michael Bronstein 

DeepMind Professor of AI at the University of Oxford

Title: Geometric deep learning: from Euclid to drug design

Thursday, August 17th, 10:15-11:15

IMP Lecture hall

Campus-Vienna-Biocenter 1, 1030 Wien

Abstract: 

Geometric Deep Learning is an attempt for geometric unification of a broad class of ML problems from the perspectives of symmetry and invariance. These principles not only underlie the breakthrough performance of convolutional neural networks and the recent success of graph neural networks but also provide a principled way to construct new problem-specific neural network architectures.

In this seminar, I will overview the mathematical principles underlying Geometric Deep Learning on grids, graphs, and manifolds, and show some of the exciting applications of these methods in the domains of structural biology and drug design.

Bio: Michael Bronstein is the DeepMind Professor of AI at the University of Oxford. He was previously a professor at USI/IDSIA and Imperial College London and held visiting appointments at Stanford, MIT, and Harvard, and has also been affiliated with three Institutes for Advanced Study (at TUM as a Rudolf Diesel Fellow (2017-2019), at Harvard as a Radcliffe fellow (2017-2018), and at Princeton as a short-time scholar (2020)). Michael received his PhD from the Technion in 2007. He is the recipient of the Turing World-Leading AI Research fellowship, Royal Society Wolfson Research Merit Award, Royal Academy of Engineering Silver Medal, five ERC grants, two Google Faculty Research Awards, and two Amazon AWS ML Research Awards. He is a Member of the Academia Europaea, Fellow of IEEE, IAPR, BCS, and ELLIS, ACM Distinguished Speaker, and World Economic Forum Young Scientist. In addition to his academic career, Michael is a serial entrepreneur and founder of multiple startup companies, including Novafora, Invision (acquired by Intel in 2012), Videocites, and Fabula AI (acquired by Twitter in 2019). In 2019-2023, he served as Head of Graph ML Research at Twitter.