Поиск :
Личный кабинет :
Электронный каталог: Papoyan, V. - Data Shift Problem in Particle Identification
Papoyan, V. - Data Shift Problem in Particle Identification

Статья
Автор: Papoyan, V.
Физика элементарных частиц и атомного ядра: Data Shift Problem in Particle Identification : [Materials of the XI International Conference “Distributed Computing and Grid Technologies in Science and Education” (GRID’2025), Dubna, July 7-11, 2025]
б.г.
ISBN отсутствует
Автор: Papoyan, V.
Физика элементарных частиц и атомного ядра: Data Shift Problem in Particle Identification : [Materials of the XI International Conference “Distributed Computing and Grid Technologies in Science and Education” (GRID’2025), Dubna, July 7-11, 2025]
б.г.
ISBN отсутствует
Статья
Papoyan, V.
Data Shift Problem in Particle Identification : [Materials of the XI International Conference “Distributed Computing and Grid Technologies in Science and Education” (GRID’2025), Dubna, July 7-11, 2025] / V.Papoyan // Физика элементарных частиц и атомного ядра. – 2026. – Т. 57, № 4. – P. 703. – URL: https://www1.jinr.ru/Pepan/v-57-4/Papoyan_ann.pdf.
Machine learning (ML) methods are increasingly applied to particle identification. Since experimental data lack ground-truth labels, classifiers are trained on Monte Carlo (MC) simulations, which leads to the problem of data shift — distributional differences between simulated and real data. The study analyzes the impact of data shift by comparing particle classification across several MC datasets with different configurations, highlighting the importance of validating and adapting ML models for robust performance
Спец.(статьи,препринты) = С 344.1ш - Методы обработки результатов измерений
Спец.(статьи,препринты) = Ц 849 - Искусственный интеллект. Теория и практика
ОИЯИ = ОИЯИ (JINR)2026
Papoyan, V.
Data Shift Problem in Particle Identification : [Materials of the XI International Conference “Distributed Computing and Grid Technologies in Science and Education” (GRID’2025), Dubna, July 7-11, 2025] / V.Papoyan // Физика элементарных частиц и атомного ядра. – 2026. – Т. 57, № 4. – P. 703. – URL: https://www1.jinr.ru/Pepan/v-57-4/Papoyan_ann.pdf.
Machine learning (ML) methods are increasingly applied to particle identification. Since experimental data lack ground-truth labels, classifiers are trained on Monte Carlo (MC) simulations, which leads to the problem of data shift — distributional differences between simulated and real data. The study analyzes the impact of data shift by comparing particle classification across several MC datasets with different configurations, highlighting the importance of validating and adapting ML models for robust performance
Спец.(статьи,препринты) = С 344.1ш - Методы обработки результатов измерений
Спец.(статьи,препринты) = Ц 849 - Искусственный интеллект. Теория и практика
ОИЯИ = ОИЯИ (JINR)2026
На полку