BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Analysis of the decay of the J/ψ meson using neural networks for 
 data analysis in particle physics.
DTSTART;VALUE=DATE-TIME:20261027T162500Z
DTEND;VALUE=DATE-TIME:20261027T163000Z
DTSTAMP;VALUE=DATE-TIME:20261029T004052Z
UID:indico-contribution-6433@cern.ch
DESCRIPTION:Speakers: Алексей Епифанов (студент)\, 
 Макар Ямпурин (Арзамасский политехничес
 кий институт (филиал) федерального госуд
 арственного бюджетного образовательног
 о учреждения высшего образования «Нижег
 ородский государственный технический у
 ниверситет им. Р.Е. Алексеева»)\nThe presented wor
 k discusses the features of the developed fully connected three-layer neur
 al network for data analysis. The model was created to process .root data 
 from the open CERN data library. The goal of this model is to identify the
  rare process of B+-meson production and its subsequent decay: B⁺ → J/
 ψ + K⁺\, J/ψ → μ⁺ + μ⁻.\n\nB⁺ mesons contain a b quark and a
 re heavy\, unstable particles. In a real experiment\, most of the recorded
  data is “background”: random combinations of particles that\, in term
 s of their kinematic characteristics\, are similar to the decay being soug
 ht. The neural network acts here as a “smart” filter that discards any
 thing that is not a decay. Several physical features are fed into it as in
 put\, and then the network calculates the probability that the event is a 
 signal. Our neural network demonstrated high accuracy values (0.977) in fi
 ltering the signal from the background\, thereby demonstrating the applica
 bility of deep learning methods in collider data analysis.\n\nhttps://indi
 co.particle.mephi.ru/event/626/contributions/6433/
LOCATION:Sevastopol hotel Conference Hall 1
URL:https://indico.particle.mephi.ru/event/626/contributions/6433/
END:VEVENT
END:VCALENDAR