BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Edge artificial intelligence for scientific instrumentation
DTSTART:20261104T140000Z
DTEND:20261104T150000Z
DTSTAMP:20261006T011900Z
UID:indico-event-40921@indico.in2p3.fr
DESCRIPTION:Speakers: Audrey Corbeil Therrien\n\nRadiation and particle de
 tectors let us observe the universe beyond what our senses can achieve. Sc
 ientists come up with new ways to collect information about our universe u
 sing detectors to transform particles into electrical signals and digital 
 bits. These novel detectors are more precise\, larger and offer much more 
 range than their predecessors\, resulting in large amounts of channels (mi
 llions) and data (>100 TB/s). Transmitting this raw data continuously to a
  compute system requires mechanical space\, energy and a significant amoun
 t hardware\, increasing costs and making some experiments non-viable. \nM
 y research group develops systems to distribute real-time compression and 
 analysis algorithms along the data acquisition chain including right up at
  the edge of the detector\, reducing data at or near the source. However\,
  this approach presents several challenges with limited computing power an
 d memory availability. We combine small AI models with carefully selected 
 signal processing and compression algorithms to achieve very efficient sma
 rt acquisition systems capable of several orders of magnitude data reducti
 on in a few microseconds. \nParticiper à la réunion Zoomhttps://ijclab.
 zoom.us/j/96755632937?pwd=VGcotFtRPnmJFK0XimbdYasAf0XrQq.1\nParticiper et 
 prendre des noteshttps://ijclab.zoom.us/j/96755632937?pwd=VGcotFtRPnmJFK0X
 imbdYasAf0XrQq.1&mynotes=on\nLien du chat de la réunionhttps://ijclab.zoo
 m.us/launch/jc/96755632937\n \n\nhttps://indico.in2p3.fr/event/40921/
LOCATION:IJCLAB
URL:https://indico.in2p3.fr/event/40921/
END:VEVENT
END:VCALENDAR
