BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:AI + HPC for Astrophysics - Maxwell Cai - Intel
DTSTART:20230518T120000Z
DTEND:20230518T133000Z
UID:TALK198325@talks.cam.ac.uk
CONTACT:James Fergusson
DESCRIPTION:Can we already use AI as a new tool to do research in astrophy
 sics? The answer to this question depends on whether we can map our astrop
 hysical problems to AI problems. Existing AI algorithms/models driven by i
 ndustrial developers can indeed be used to tackle some (but not all) astro
 physical problems that are data-intensive\, compute-intensive\, or both. N
 evertheless\, due to the unique properties of physics data\, adapting AI f
 or astrophysics is by no means frictionless. In this talk\, I will review 
 the journey of astrophysical research from analytical models to empirical 
 models\, to data-driven discovery of physical laws\, and eventually to aug
 menting AI models with inductive biases. I will also talk about upscaling 
 AI models to massively parallel computers\, an interplay of HPC and AI tha
 t makes training large models and ingesting huge datasets possible.
LOCATION:Hoyle Lecture Theatre\, Institute of Astronomy\, Madingley Rise
END:VEVENT
END:VCALENDAR