Cargando…
Leveraging universality of jet taggers through transfer learning
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 common to dif...
Autores principales: | Dreyer, Frédéric A., Grabarczyk, Radosław, Monni, Pier Francesco |
---|---|
Lenguaje: | eng |
Publicado: |
2022
|
Materias: | |
Acceso en línea: | https://dx.doi.org/10.1140/epjc/s10052-022-10469-9 http://cds.cern.ch/record/2804029 |
Ejemplares similares
-
Jet tagging in the Lund plane with graph networks
por: Dreyer, Frédéric A., et al.
Publicado: (2020) -
Towards Optimal Compression: Joint Pruning and Quantization
por: Zandonati, Ben, et al.
Publicado: (2023) -
Technical Report of Participation in Higgs Boson Machine Learning Challenge
por: Ahmad, S. Raza
Publicado: (2015) -
Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark
por: Borras, Hendrik, et al.
Publicado: (2022) -
Lightweight Jet Reconstruction and Identification as an Object Detection Task
por: Pol, Adrian Alan, et al.
Publicado: (2022)