BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:"Machine learning in chemistry and beyond" (ChE-651) seminar by Ri
 si Kondor (University of Chicago)
DTSTART:20220308T151500
DTEND:20220308T161500
DTSTAMP:20260610T042626Z
UID:6b6beb26ddc0949429861c8321e13b2252b90493be7722d75f8fdad5
CATEGORIES:Conferences - Seminars
DESCRIPTION:Risi Kondor\n\nRisi Kondor’s work is centered on basic machi
 ne learning methodology\, often inspired by ideas from algebra and computa
 tional harmonic analysis. In recent years\, much of the work in Risi’s l
 ab has focused on the rapidly growing intersection between machine learnin
 g and science\, including novel graph neural network architectures for che
 mistry\, machine learning approaches to learning molecular force fields\, 
 and neural network approximations to quantum states. As part of this endea
 vor\, his group has made foundational contributions to the theory of group
  equivariant neural networks\, which are used in physics and chemistry\, a
 s well as computer vision and medical imaging. An integral part of the gro
 up’s work is the development of high performance\, open source software 
 libraries.\nRisi is a member of both the Computer Science Department and t
 he Computational and Applied Mathematics group in the Department of Statis
 tics. He received his BA in mathematics from Cambridge and his PhD in comp
 uter science from Columbia University\, followed by postdoctoral appointme
 nts at the Gatsby Unit (UCL) and the Center for the Mathematics of Informa
 tion at Caltech. He also has a diploma in computational fluid dynamics fro
 m the Von Karman Institute and an MS in machine learning from Carnegie Mel
 lon University. Risi has also worked in the deep learning team at Amazon W
 eb Services and the Center for Computational Mathematics at the Flatiron I
 nstitute.
LOCATION:https://epfl.zoom.us/j/64473017589?pwd=Vmpnd1pleGhEb1hFb3kxUlNIUW
 JyQT09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR