BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:AI-assisted experiment design and optimization at the frontiers of
  computation: new perspectives in fundamental and medical physics
DTSTART;VALUE=DATE-TIME:20260908T070000Z
DTEND;VALUE=DATE-TIME:20260908T074000Z
DTSTAMP;VALUE=DATE-TIME:20260922T182728Z
UID:indico-contribution-2050@events.ncbj.gov.pl
DESCRIPTION:Speakers: Pietro Vischia (Departamento de Fïsica y ICTEA\, Un
 iversidad de Oviedo)\nDesigning the next generation colliders and detector
 s involves solving optimization problems in high-dimensional spaces where 
 the optimal solutions may nest in regions that human experts would normall
 y not explore. Meanwhile\, the staggering simulation demands of existing a
 nd future high-energy physics facilities call for a new paradigm for event
  generation and reconstruction.\n\nDifferentiable programming offers a pat
 h forward. By integrating domain knowledge encoded in simulation software 
 with gradient-based optimization and reinforcement learning\, it enables e
 nd-to-end experimental design and inference in settings that are intractab
 le with conventional methods.\n\nIn this talk I will describe recent resul
 ts for the AI-assisted optimization of experimental design\, with a focus 
 on large-scale simulation software\, touching on recent advances in calori
 metry with neuromorphic hardware architectures\, and on medical applicatio
 ns\, paving the way to more complex challenges.\n\nhttps://events.ncbj.gov
 .pl/event/468/contributions/2050/
LOCATION:
URL:https://events.ncbj.gov.pl/event/468/contributions/2050/
END:VEVENT
END:VCALENDAR