BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Geometric Principles for Machine Learning Physical Systems - Dr Za
 ck X Conti\, Alan Turing Institute
DTSTART:20250613T150000Z
DTEND:20250613T160000Z
UID:TALK229963@talks.cam.ac.uk
CONTACT:46601
DESCRIPTION:From classical mechanics\, we know that mathematical descripti
 ons of dynamical systems are deeply rooted in topological spaces defined b
 y non-Euclidean geometry. In this talk we will investigate how these struc
 ture-rich\, geometric representations could be key to improving generaliza
 tion and parsimony when using machine learning to model physical systems f
 rom data.\n
LOCATION:JDB Seminar Room\, CUED
END:VEVENT
END:VCALENDAR