BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:CIS - Colloquium -  by Prof Michael Bronstein
DTSTART:20210510T151500
DTEND:20210510T161500
DTSTAMP:20260507T200500Z
UID:4ee216854df7aa9379d6630d7c3609e9cdf37765b337a2f77aa0d0da
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Michael Bronstein\nTitle: Geometric Deep Learning: from 
 Euclid to drug design\n\nAbstract: For nearly two millennia\, the word "ge
 ometry" was synonymous with Euclidean geometry\, as no other types of geom
 etry existed. Euclid's monopoly came to an end in the 19th century\, where
  multiple examples of non-Euclidean geometries were shown. However\, these
  studies quickly diverged into disparate fields\, with mathematicians deba
 ting the relations between different geometries and what defines one. A wa
 y out of this pickle was shown by Felix Klein in his Erlangen Programme\, 
 which proposed approaching geometry as the study of invariants or symmetri
 es using the language of group theory. In the 20th century\, these ideas h
 ave been fundamental in developing modern physics\, culminating in the Sta
 ndard Model. \n\nThe current state of deep learning somewhat resembles th
 e situation in the field of geometry in the 19h century: On the one hand\,
  in the past decade\, deep learning has brought a revolution in data scien
 ce and made possible many tasks previously thought to be beyond reach -- i
 ncluding computer vision\, playing Go\, or protein folding. At the same ti
 me\, we have a zoo of neural network architectures for various kinds of da
 ta\, but few unifying principles. As in times past\, it is difficult to un
 derstand the relations between different methods\, inevitably resulting in
  the reinvention and re-branding of the same concepts.  \n\nGeometric De
 ep Learning aims to bring geometric unification to deep learning in the sp
 irit of the Erlangen Programme. Such an endeavour serves a dual purpose: i
 t provides a common mathematical framework to study the most successful ne
 ural network architectures\, such as CNNs\, RNNs\, GNNs\, and Transformers
 \, and gives a constructive procedure to incorporate prior knowledge into 
 neural networks and build future architectures in a principled way. In thi
 s talk\, I will overview the mathematical principles underlying Geometric 
 Deep Learning on grids\, graphs\, and manifolds\, and show some of the exc
 iting and groundbreaking applications of these methods in the domains of c
 omputer vision\, social science\, biology\, and drug design. \n\n(based o
 n joint work with J. Bruna\, T. Cohen\, P. Veličković)\n\n\nBio: Michael
  Bronstein is a professor at Imperial College London\, where he holds the 
 Chair in Machine Learning and Pattern Recognition\, and Head of Graph Lear
 ning Research at Twitter. He also heads ML research in Project CETI\, a TE
 D Audacious Prize-winning collaboration aimed at understanding the communi
 cation of sperm whales. Michael received his PhD from the Technion in 2007
 . He has 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 is 
 the recipient of the Royal Society Wolfson Research Merit Award\, Royal Ac
 ademy of Engineering Silver Medal\, five ERC grants\, two Google Faculty R
 esearch Awards\, and two Amazon AWS ML Research Awards. He is a Member of 
 the Academia Europaea\, Fellow of IEEE\, IAPR\, BCS\, and ELLIS\, ACM Dist
 inguished Speaker\, and World Economic Forum Young Scientist. In addition 
 to his academic career\, Michael is a serial entrepreneur and founder of m
 ultiple startup companies\, including Novafora\, Invision (acquired by Int
 el in 2012)\, Videocites\, and Fabula AI (acquired by Twitter in 2019). He
  has previously served as Principal Engineer at Intel Perceptual Computing
  and was one of the key developers of the Intel RealSense technology.\n\n\
 nThe Center for Intelligent Systems at EPFL (CIS) is a collaboration among
  IC\,ENAC\, SB\, SV and STI that brings together researchers working on di
 fferent aspects of Intelligent Systems. In June 2020\, CIS has launched it
 s CIS Colloquia featuring invited notable speakers.\nMore info https://www
 .epfl.ch/research/domains/cis/center-for-intelligent-systems-cis/events/co
 lloquia-2/prof-michael-bronstein/\n 
LOCATION:Zoom https://epfl.zoom.us/meeting/register/u5UudOGoqjguGd3Ab-y0_D
 XTKGqx842pUJri https://epfl.zoom.us/meeting/register/u5UudOGoqjguGd3Ab-y0_
 DXTKGqx842pUJri
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR