BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:(Machine)-learning the galactic potential
DTSTART;VALUE=DATE-TIME:20230320T094300Z
DTEND;VALUE=DATE-TIME:20230320T094500Z
DTSTAMP;VALUE=DATE-TIME:20240704T115712Z
UID:indico-contribution-296@meetings.aip.de
DESCRIPTION:Speakers: Wassim Tenachi (Observatoire de Strasbourg)\nRecent 
 observational efforts such as Gaia are leading us toward a new era of data
  abundance which offers us an incredible opportunity for discovering new p
 hysics. Thanks to recent advances in the field of machine learning\, it is
  possible to extract valuable information from the colossal amount of data
  now available.\nIn particular\, auto-differentiation allows us to get a b
 etter grasp of galactic dynamics. It might even enable us to capture a pre
 cise and agnostic map of the gravitational potential of the Milky-Way and 
 the underlying dark matter distribution from a mere snapshot of stellar po
 sitions and velocities.\nHowever\, machine learning in the context of phys
 ics is both plagued and blessed by one of its most potent components: neur
 al networks\, which are extremely powerful and flexible for modelling phys
 ical systems but largely consist in non-interpretable black boxes. Thus\, 
 a complementary approach based on symbolic regression is currently being b
 uilt in the goal of recovering the analytical expression describing a pote
 ntial. We will present a preliminary study of these new approaches.\n\nhtt
 ps://meetings.aip.de/event/20/contributions/296/
LOCATION:Haus H\, Telegrafenberg
URL:https://meetings.aip.de/event/20/contributions/296/
END:VEVENT
END:VCALENDAR