BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:The Transformer and its uses in High Energy Physics
DTSTART:20261022T120000Z
DTEND:20261022T130000Z
DTSTAMP:20261007T090100Z
UID:indico-event-40310@indico.in2p3.fr
DESCRIPTION:Speakers: Corentin Allaire (IJCLab\, Université Paris-Saclay\
 , CNRS/IN2P3)\n\nThe transformer network\, proposed by Google scientists i
 n 2017 in the « Attention Is All You Need »\, has become a game-changer 
 in the field of Deep learning. Originally developed for natural language t
 ranslation\, they became the cornerstone of all modern Large Language Mode
 ls. While those models are extremely good at handling language-based input
 \, they can also be quite performant at handling physics data. In this sem
 inar\, after a small reminder on the basics of deep learning\, we will be 
 introducing the Transformer\, how it works\, how one can build/train one f
 rom scratch and what tasks it is well-suited for. All this while\, taking\
 , for example\, the field of High Energy Physics. A domain well known for 
 its large volume of data and pioneering use of Deep Learning technology.\n
 \nhttps://indico.in2p3.fr/event/40310/
LOCATION:Amphi PASCAL (Subatech IMT Atlantique)
URL:https://indico.in2p3.fr/event/40310/
END:VEVENT
END:VCALENDAR