Resource-efficient inference for particle physics - Archive ouverte HAL
Article Dans Une Revue Nature Machine Intelligence Année : 2021

Resource-efficient inference for particle physics

Résumé

Selecting interesting proton–proton collisions from the millions taking place each second in the Large Hadron Collider is a challenging task. A neural network optimized for a field-programmable gate array hardware enables 60 ns inference and reduces power consumption by a factor of 50.
Fichier non déposé

Dates et versions

hal-03336593 , version 1 (07-09-2021)

Identifiants

Citer

David Rousseau. Resource-efficient inference for particle physics. Nature Machine Intelligence, 2021, 3 (8), pp.656-657. ⟨10.1038/s42256-021-00381-4⟩. ⟨hal-03336593⟩
19 Consultations
0 Téléchargements

Altmetric

Partager

More