BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:PHYSTAT Seminar: AI for general Physics and Engineering
DTSTART:20260520T140000Z
DTEND:20260520T153000Z
DTSTAMP:20260517T140400Z
UID:indico-event-1642992@indico.cern.ch
DESCRIPTION:Speakers: Mishra Siddhartha (ETH Zurich)\n\nAbstract: \nAbstr
 act: Partial Differential Equations (PDEs) are often described as the lang
 uage of Physics as they describe a wide array of physical phenomena over
  a vast range of scales. Despite their remarkable success over many decade
 s\, numerical methods for approximating PDEs can incur a very high computa
 tional cost. This limitation has provided the impetus for the design of fa
 st and accurate Machine Learning/AI based neural PDE surrogates which can
  learn the PDE solution operator from data. In this talk\, we review some 
 latest developments in the field of Neural Operators\, which are widely us
 ed as an ML paradigm for PDEs and discuss state of the art neural operator
 s based on convolutions or attention. We will discuss graph and transforme
 r based architectures for PDEs on arbitrary domains and conditional Diffus
 ion models for PDEs with chaotic multiscale solutions.  Finally\, the iss
 ue of sample complexity is addressed by the design of general purpose Foun
 dation models for PDEs. \n \n\n\nhttps://indico.cern.ch/event/1642992/\n
 \nZoom: https://cern.zoom.us/j/68793225561?pwd=MHBxOStiUnYvZitTRWdvZ05YdkZ
 wUT09
URL:https://indico.cern.ch/event/1642992/
END:VEVENT
END:VCALENDAR