Speaker
Alberto Bragagnolo
(CERN)
Description
Develop state-of-the-art NN for flavour inference of neutral B mesons for CKM CPV analyses, evolution of work performed in BPH-23-004. NNs are used as probability estimators, so perfect calibration is as important as performance. To be deployed in flagship BPH analyses.
CERN group/ Experiment
EP-CMG
| Working area | Area 1" Cutting Edge AI for Offline Data Processing |
|---|---|
| Project goals | Apply the latest state-of-the-art model (e.g. transformers) in place of outdated architectures (DeepSets, Fully Connected Dense layers) to improve performance. Standardise deployment on NanoAOD format for wider usage in CMS. |
| Timeline | 1 year |
| Available person power | 2 fellows (~25% of the time), 2 users (~25% of the time) |
| Additional person power request | none |
| Is this an already ongoing activity? | Yes |
| Indicative hardware resources needs | Access to a GPU cluster with LCG-like software stack and cvmfs access with fast storage facilities |
Authors
Alberto Bragagnolo
(CERN)
Enrico Lusiani
(Universita e INFN, Padova (IT))
Georgios Karathanasis
(CERN)
Maurizio Pierini
(CERN)
Paris Sphicas
(CERN/Athens)
Pietro Grutta
(University of Padua, INFN)