# Quark/gluon jet discrimination: a reproducible analysis using R

- Institution: CERN
- Department: Machine Learning
- Speaker: Andrew Lowe
- Year: 2017
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3006446)
- 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)

The power to discriminate between light-quark jets and gluon jets would have a huge impact on many searches for new physics at CERN and beyond. This talk will present a walk-through of the development of a prototype machine learning classifier for differentiating between quark and gluon jets at experiments like those at the Large Hadron Collider at CERN. A new fast feature selection method that combines information theory and graph analytics will be outlined. This method has found new variables that promise significant improvements in discrimination power. The prototype jet tagger is simple, interpretable, parsimonious, and computationally extremely cheap, and therefore might be suitable for use in trigger systems for real-time data processing. Nested stratified k-fold cross validation was used to generate robust estimates of model performance. The data analysis was performed entirely in the R statistical programming language, and is fully reproducible. The entire analysis workflow is data-driven, automated and runs on very modest hardware with no human intervention. New data visualisation techniques will also be introduced..

0:00:00 Slide 1

0:00:58 Slide 2

0:01:39 Slide 3

0:02:22 Slide 4

0:03:32 Slide 5

0:04:23 Slide 6

0:05:43 Slide 7

0:06:01 Slide 8

0:06:34 Slide 9

0:06:59 Slide 10

0:07:20 Slide 11

0:07:37 Slide 12

0:08:51 Slide 13

0:09:39 Slide 14

0:09:45 Slide 15

0:10:06 Slide 16

0:11:01 Slide 17

0:11:27 Slide 18

0:11:49 Slide 19

0:14:06 Slide 20

0:15:41 Slide 21

0:16:11 Slide 22

0:16:32 Slide 23

0:17:29 Slide 24

0:18:00 Slide 25

0:18:28 Slide 26

0:19:05 Slide 27

0:20:38 Slide 28

0:21:23 Slide 29

0:21:51 Slide 30

0:22:31 Slide 31

0:22:38 Slide 32

0:23:37 Slide 33

0:24:58 Slide 34

0:25:08 Slide 35

0:26:46 Slide 36

0:27:55 Slide 37

0:28:23 Slide 38

0:28:57 Slide 39

## Lectures

1. [Quark/gluon jet discrimination: a reproducible analysis using R](https://invisiblenetwork.ai/learn/cern/3006446/f1c123ff363d), 43 min (CERN's player)