English

Learning to Identify Electrons

Data Analysis, Statistics and Probability 2021-07-07 v2 High Energy Physics - Experiment High Energy Physics - Phenomenology

Abstract

We investigate whether state-of-the-art classification features commonly used to distinguish electrons from jet backgrounds in collider experiments are overlooking valuable information. A deep convolutional neural network analysis of electromagnetic and hadronic calorimeter deposits is compared to the performance of typical features, revealing a 5%\approx 5\% gap which indicates that these lower-level data do contain untapped classification power. To reveal the nature of this unused information, we use a recently developed technique to map the deep network into a space of physically interpretable observables. We identify two simple calorimeter observables which are not typically used for electron identification, but which mimic the decisions of the convolutional network and nearly close the performance gap.

Keywords

Cite

@article{arxiv.2011.01984,
  title  = {Learning to Identify Electrons},
  author = {Julian Collado and Jessica N. Howard and Taylor Faucett and Tony Tong and Pierre Baldi and Daniel Whiteson},
  journal= {arXiv preprint arXiv:2011.01984},
  year   = {2021}
}

Comments

10 pages, lots of figures, v2 for submission

R2 v1 2026-06-23T19:53:54.914Z