English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We describe a novel application of the end-to-end deep learning technique tothe task of discriminating top quark-initiated jets from those originating fromthe hadronization of a light quark or a gluon. The end-to-end deep learningtechnique combines deep learning algorithms and low-level detectorrepresentation of the high-energy collision event. In this study, we uselow-level detector information from the simulated CMS Open Data samples toconstruct the top jet classifiers. To optimize classifier performance weprogressively add low-level information from the CMS tracking detector,including pixel detector reconstructed hits and impact parameters, anddemonstrate the value of additional tracking information even when no newspatial structures are added. Relying only on calorimeter energy deposits andreconstructed pixel detector hits, the end-to-end classifier achieves an AUCscore of 0.975$\pm$0.002 for the task of classifying boosted top quark jets.After adding derived track quantities, the classifier AUC score increases to0.9824$\pm$0.0013, serving as the first performance benchmark for these CMSOpen Data samples. We additionally provide a timing performance comparison ofdifferent processor unit architectures for training the network.

End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data