Abstract
AbstractATLAS collaboration uses machine learning (ML) algorithms in many different ways in its physics programme, starting from object reconstruction, simulation of calorimeter showers, signal to background discrimination in searches and measurements, tagging jets based on their origin and so on. Anomaly detection (AD) techniques are also gaining popularity where they are used to find hidden patterns in the data, with lesser dependence on simulated samples as in the case of supervised learning-based methods. ML methods used in detector simulation and in jet tagging in ATLAS will be discussed, along with four searches using ML/AD techniques.
Funder
Royal Society
University of the Witwatersrand
Publisher
Springer Science and Business Media LLC
Reference39 articles.
1. S. Badger et al., Machine learning and LHC event generation. SciPost Phys. 14(4), 079 (2023). https://doi.org/10.21468/SciPostPhys.14.4.079. arXiv:2203.07460 [hep-ph]
2. J.M. Campbell et al., Event generators for high-energy physics experiments. In: Snowmass 2021 (2022)
3. S. Agostinelli et al., GEANT4-a simulation toolkit. Nucl. Instrum. Methods A 506, 250–303 (2003). https://doi.org/10.1016/S0168-9002(03)01368-8
4. ATLAS Collaboration, AtlFast3: the next generation of fast simulation in ATLAS. Comput. Softw. Big Sci. 6, 7 (2021). https://doi.org/10.1007/s41781-021-00079-7. arXiv:2109.02551 [hep-ex]
5. ATLAS Collaboration, Deep generative models for fast shower simulation in ATLAS. ATL-SOFT-PUB-2018-001 (CERN, Geneva, 2018). https://cds.cern.ch/record/2630433