Leveraging universality of jet taggers through transfer learning
Abstract A significant challenge in the tagging of boosted objects via machine-learning technology is the prohibitive computational cost associated with training sophisticated models. Nevertheless, the universality of QCD suggests that a large amount of the information learnt in the training is comm...
Main Authors: | Frédéric A. Dreyer, Radosław Grabarczyk, Pier Francesco Monni |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2022-06-01
|
Series: | European Physical Journal C: Particles and Fields |
Online Access: | https://doi.org/10.1140/epjc/s10052-022-10469-9 |
Similar Items
-
Deep-learning top taggers or the end of QCD?
by: Gregor Kasieczka, et al.
Published: (2017-05-01) -
Deep Learning based Tamil Parts of Speech (POS) Tagger
by: S. Anbukkarasi, et al.
Published: (2021-09-01) -
Parallel Bidirectionally Pretrained Taggers as Feature Generators
by: Ranka Stanković, et al.
Published: (2022-05-01) -
Building a better boosted top tagger
by: Larkoski, Andrew, et al.
Published: (2015) -
Part-of-speech tagger for Malay social media texts
by: Siti Noor Allia Noor Ariffin,, et al.
Published: (2018)