Back to search

Institutional Repository of Vilnius University

Aukštos energijos fizikos duomenų generavimas naudojant giliuosius neuroninius tinklus /

Abstract

dc:description

This paper examines the generation of high‐energy physics particles using artificial neural network methods. In high‐energy physics experiments (e.g. the CMS experiment at CERN), generating large volumes of such data often relies on Monte Carlo simulations that require very high computing resources. To reduce the computational cost of such simulations, this work investigates the use of generative neural networks for synthetic data generation. Generative adversarial networks (GANs) and their conditional variant (CGAN) were developed and tested for generating particle physics data. The models were trained on data from the CMS experiment, and the synthetic data produced were compared with the original distributions of particle properties. The results showed that the best performance was achieved by a conditional GAN with a three‐layer architecture. The data generated by this model most closely matched the true distributions according to Jensen–Shannon divergence and Wasserstein’s and Hellinger’s distances, outperforming the standard GAN. These results demonstrate the potential of generative neural network models to produce data more quickly for future particle physics research, reducing the burden on traditional Monte Carlo simulations.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Eglynas, Erikas,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Eglynas, Erikas,. Aukštos energijos fizikos duomenų generavimas naudojant giliuosius neuroninius tinklus /. Institutional Repository of Vilnius University, 2025. https://repository.vu.lt/VU:ELABAETD239030253&prefLang=en_US