SciPost Submission Page
Reports of My Demise Are Greatly Exaggerated: $N$-subjettiness Taggers Take On Jet Images
by Liam Moore, Karl Nordström, Sreedevi Varma, Malcolm Fairbairn
- Published as SciPost Phys. 7, 036 (2019)
Submission summary
As Contributors: | Sreedevi Varma |
Arxiv Link: | https://arxiv.org/abs/1807.04769v3 |
Date accepted: | 2019-09-04 |
Date submitted: | 2019-08-08 |
Submitted by: | Varma, Sreedevi |
Submitted to: | SciPost Physics |
Discipline: | Physics |
Subject area: | High-Energy Physics - Phenomenology |
Approaches: | Experimental, Theoretical, Computational |
Abstract
We compare the performance of a convolutional neural network (CNN) trained on jet images with dense neural networks (DNNs) trained on n-subjettiness variables to study the distinguishing power of these two separate techniques applied to top quark decays. We find that they perform almost identically and are highly correlated once jet mass information is included, which suggests they are accessing the same underlying information which can be intuitively understood as being contained in 4-, 5-, 6-, and 8-body kinematic phase spaces depending on the sample. This suggests both of these methods are highly useful for heavy object tagging and provides a tentative answer to the question of what the image network is actually learning.
Ontology / Topics
See full Ontology or Topics database.Published as SciPost Phys. 7, 036 (2019)
Submission & Refereeing History
Reports on this Submission
Anonymous Report 1 on 2019-8-24 Invited Report
Report
I thank the authors for suitably addressing my comments and questions. The present version of the manuscript is much improved, and I now recommend it for publication in SciPost.