CapsNets continuing the convolutional quest
Capsule networks are ideal tools to combine event-level and subjet information at the LHC. After benchmarking our capsule network against standard convolutional networks, we show how multi-class capsules extract a resonance decaying to top quarks from both, QCD di-jet and the top continuum backgroun...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
07-02-2020
|
| In: |
SciPost physics
Year: 2020, Jahrgang: 8, Heft: 2, Pages: 1-22 |
| ISSN: | 2542-4653 |
| DOI: | 10.21468/SciPostPhys.8.2.023 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.21468/SciPostPhys.8.2.023
|
| Verfasserangaben: | Sascha Diefenbacher, Hermann Frost, Gregor Kasieczka, Tilman Plehn and Jennifer M. Thompson |
| Zusammenfassung: | Capsule networks are ideal tools to combine event-level and subjet information at the LHC. After benchmarking our capsule network against standard convolutional networks, we show how multi-class capsules extract a resonance decaying to top quarks from both, QCD di-jet and the top continuum backgrounds. We then show how its results can be easily interpreted. Finally, we use associated top-Higgs production to demonstrate that capsule networks can work on overlaying images to go beyond calorimeter information. |
|---|---|
| Beschreibung: | Gesehen am 11.09.2020 |
| Beschreibung: | Online Resource |
| ISSN: | 2542-4653 |
| DOI: | 10.21468/SciPostPhys.8.2.023 |