BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Searching for bumps and classifying jets in the ATLAS experiment
DTSTART:20260507T123000Z
DTEND:20260507T133000Z
DTSTAMP:20260512T085300Z
UID:indico-event-39179@indico.in2p3.fr
DESCRIPTION:Speakers: Eva Mayer (Université Clermont Auvergne)\n\nThis ta
 lk presents two machine learning developments targeting distinct challenge
 s in ATLAS data analysis. \nFirst\, a multiclass tagger for large-radius 
 jets\, capable of simultaneously discriminating top quark\, W\, Z\, and Hi
 ggs boson jets from the overwhelming QCD multijet background within a sing
 le unified model is presented.\nSecond\, I introduce BumpNet\, a CNN-based
  approach to resonance searches that learns to identify localised excesses
  in invariant mass distributions. The network is trained on the likelihood
  ratio between a smoothly falling background distribution and one with a n
 arrow bump injected\, enabling it to scan hundreds of histograms for poten
 tial signals in a fast and automated way.\nTogether\, these tools illustra
 te how modern deep learning can both sharpen our sensitivity to known phys
 ics objects and broaden our reach for new phenomena.\n \n\n\nhttps://indi
 co.in2p3.fr/event/39179/
LOCATION:Amphi 125 EUPI
URL:https://indico.in2p3.fr/event/39179/
END:VEVENT
END:VCALENDAR