E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% of decisions and yielding gains over baseline PCN.
Francescato et al.,Model compression and simplification pipelines for fast deep neural network inference in FPGAs in HEP,The European Physical Journal C81(2021) 1005
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
hep-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
E-PCN: Jet Tagging with Explainable Particle Chebyshev Networks Using Kinematic Features
E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% of decisions and yielding gains over baseline PCN.