TY  - CONF
AU  - Blekman, Freya
AU  - Gautam, Kunal
AU  - Ploerer, Eduardo
AU  - Canelli, Florencia
AU  - De Moor, Alexandre
AU  - Ilg, Armin
AU  - Macchiolo, Anna
TI  - Tagging each jet flavour at FCC-ee with a Transformer-based Neural Network
M1  - PUBDB-2024-07404
PY  - 2024
AB  - Jet flavour tagging is crucial in experimental high-energy physics. A tagging algorithm, DeepJetTransformer, is presented, which exploits a transformer-based neural network that is substantially faster to train.The DeepJetTransformer network uses information from particle flow-style objects and secondary vertex reconstruction as is standard for- and -jet identification supplemented by additional information, such as reconstructed Vs and discrimination, typically not included in tagging algorithms at the LHC. The model is trained as a multiclassifier to identify all quark flavours separately and performs excellently in identifying - and -jets. An -tagging efficiency of can be achieved with a -jet background efficiency. The impact of including Vs anddiscrimination is presented.The network is applied on exclusivesamples to examine the physics potential and is shown to isolateevents. Assuming all other backgrounds can be efficiently rejected, a discovery significance forcan be achieved with an integrated luminosity of , corresponding to less than a second of the FCC-ee run plan at the resonance.
T2  - 3rd ECFA Workshop on e+e- Higgs, Top & ElectroWeak Factories
CY  - 9 Oct 2024 - 11 Oct 2024, Paris (France)
Y2  - 9 Oct 2024 - 11 Oct 2024
M2  - Paris, France
LB  - PUB:(DE-HGF)6
UR  - https://bib-pubdb1.desy.de/record/619117
ER  -