Jul 6 – 8, 2021
Europe/Zurich timezone

Supervised Attention for Jet Classification

Jul 6, 2021, 10:40 AM


Jonathan Shlomi (Weizmann Institute of Science (IL))


Secondary vertex reconstruction is a key intermediate step in building powerful jet classifiers. We use a neural network to perform vertex finding inside jets in order to improve classification performance. This can be thought of as a supervised attention mechanism - directing the classifier towards the relevant information inside the jet. We show supervised attention outperforms an identical network with standard unsupervised attention.


Academic Rank PhD student
Affiliation Weizmann Institute

Primary authors

Eilam Gross (Weizmann Institute of Science (IL)) Jonathan Shlomi (Weizmann Institute of Science (IL)) Kyle Stuart Cranmer (New York University (US)) Sanmay Ganguly (Weizmann Institute of Science (IL))

Presentation materials