BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Offline electron identification using a Deep Neural Network (12+3)
DTSTART;VALUE=DATE-TIME:20241202T143500Z
DTEND;VALUE=DATE-TIME:20241202T144700Z
DTSTAMP;VALUE=DATE-TIME:20260419T223014Z
UID:indico-contribution-25592@indico.ific.uv.es
DESCRIPTION:Speakers: Enrique Valiente Moreno (CSIC-IFIC (UV))\nPreviously
  in ATLAS a likelihood approach has been used for prompt electron identifi
 cation against different possible backgrounds.\nOver the last few years\, 
 great efforts have been made in order to develop a versatile\, powerful an
 d reliable deep neural network (DNN) that is able to perform a multinomial
  classification of electrons according to different pre-defined classes. O
 nce this machine learning algorithm learns the fundamental characteristics
  of each electron type\, different discriminants can be built out of the m
 ultinomial scores given by the DNN in order to decide to decide whether an
  electron can be identifed as prompt within a pre-defined efficiency.\n\nh
 ttps://indico.ific.uv.es/event/7807/contributions/25592/
LOCATION:Universe 1001-Primera-1-1-1 - Paterna. Seminario
URL:https://indico.ific.uv.es/event/7807/contributions/25592/
END:VEVENT
END:VCALENDAR