# DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets

- Institution: CERN
- Department: Machine Learning
- Taught by: Loukas Gouskos, Huilin Qu, Markus Stoye, Jan Kieseler, Mauro Verzetti
- Year: 2018
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3009384)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

We present a customized neural network architecture for both, slim and fat jet tagging. It is based on the idea to keep the concept of physics objects, like particle flow particles, as a core element of the network architecture. The deep learning algorithm works for most of the common jet classes, i.e. b, c, usd and gluon jets for slim jets and W, Z, H, QCD and top classes for fat jets. The developed architecture promising gains in performance as shown in simulation of the CMS collaboration. Currently the tagger is under test in real data in the CMS experiment..

0:00:00 Slide 1

0:00:22 Slide 2

0:00:29 Slide 3

0:00:37 Slide 4

0:02:08 Slide 5

0:03:31 Slide 6

0:04:29 Slide 7

0:05:10 Slide 8

0:05:44 Slide 9

0:06:05 Slide 10

0:06:40 Slide 11

0:07:04 Slide 12

0:08:06 Slide 13

0:09:38 Slide 14

0:09:55 Slide 15

0:10:04 Slide 16

0:10:18 Slide 17

0:10:29 Slide 18

0:11:44 Slide 19

0:11:57 Slide 20

0:13:17 Slide 21

0:13:41 Slide 22

0:14:01 Slide 23

0:15:34 Slide 24

0:17:53 Slide 25

0:21:03 Slide 26

0:21:07 Slide 27

0:22:57 Slide 28

0:23:54 Slide 29

## Lectures

1. [DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets](https://invisiblenetwork.ai/learn/cern/3009384/7a012a135cb9), 27 min (CERN's player)