BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Deep Learning Method for Determining EAS Parameters in TAIGA HiSCO
 RE
DTSTART;VALUE=DATE-TIME:20241024T151500Z
DTEND;VALUE=DATE-TIME:20241024T153000Z
DTSTAMP;VALUE=DATE-TIME:20260518T065901Z
UID:indico-contribution-4210@cern.ch
DESCRIPTION:Speakers: Alexandr Kryukov (SINP MSU)\nThe TAIGA-HiSCORE setup
  is an array of wide-angle Cherenkov detectors. It contains more than a hu
 ndred stations located in the Tunka Valley. The effective area of ​​th
 e setup is about 1 sq. km. The HiSCORE setup is designed to register cosmi
 c particles and gamma quanta with TeV energies. Each station records a lar
 ge amount of data\, including the signal arrival time and its amplitude. P
 rimary data analysis includes the reconstruction of EAS parameters. These 
 are the EAS axis direction\, the type of primary particle\, and its energy
 . In this report\, we propose using the deep learning method to reconstruc
 t the EAS parameters recorded by HiSCORE. Using the example of determining
  the EAS axis direction\, we will consider two approaches based on deep ne
 ural networks. One of them is based on representing a set of time stamps a
 s an image and processing such data using convolutional neural networks. T
 he other approach uses fully connected deep neural networks to solve the r
 egression problem based on time stamps. Both approaches are shown to yield
  results comparable to traditional data analysis methods.\n\nhttps://indic
 o.particle.mephi.ru/event/436/contributions/4210/
LOCATION: Moskvorechye 1
URL:https://indico.particle.mephi.ru/event/436/contributions/4210/
END:VEVENT
END:VCALENDAR