Cargando…
Studies to mitigate difference between real data and simulation for jet tagging
<!--HTML-->The aim of the studies presented is to improve the performance of jet flavour tagging on real data while still exploiting a simulated dataset for the learning of the main classification task. In the presentation we explore “off the shelf” domain adaptation techniques as well as cust...
Autores principales: | Buchmuller, Oliver, Martelli, Arabella, Kieseler, Jan, Verzetti, Mauro, Stoye, Markus |
---|---|
Lenguaje: | eng |
Publicado: |
2018
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2315380 |
Ejemplares similares
-
DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets
por: Gouskos, Loukas, et al.
Publicado: (2018) -
Jet reconstruction and heavy jet tagging at LHCb
por: Sestini, Lorenzo
Publicado: (2017) -
Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
por: Shimmin, Chase Owen
Publicado: (2017) -
Exploring neural networks to improve b-jet tagging with the ALICE detector
por: Haake, Rudiger
Publicado: (2017) -
DeepFlavour in CMS
por: Stoye, Markus
Publicado: (2017)