TL;DR
This paper demonstrates that deep neural networks can extract additional valuable information from calorimeter data to improve electron identification in collider experiments, surpassing traditional features.
Contribution
It introduces a deep learning approach that uncovers previously unused calorimeter observables, enhancing electron classification performance.
Findings
Deep neural networks outperform traditional features by about 5% in classification accuracy.
Two new calorimeter observables are identified that mimic neural network decisions.
The approach reveals untapped information in calorimeter data for particle identification.
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 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
