# Application of Generative Adversarial Networks (GANs) to jet images

- Institution: CERN
- Department: Machine Learning
- Speaker: Michela Paganini
- Year: 2017
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3017307)
- 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)

https://arxiv.org/abs/1701.05927

We provide a bridge between generative modeling in the Machine Learning community and simulated physical processes in High Energy Particle Physics by applying a novel Generative Adversarial Network (GAN) architecture to the production of jet images -- 2D representations of energy depositions from particles interacting with a calorimeter. We propose a simple architecture, the Location-Aware Generative Adversarial Network, that learns to produce realistic radiation patterns from simulated high energy particle collisions. The pixel intensities of GAN-generated images faithfully span over many orders of magnitude and exhibit the desired low-dimensional physical properties (i.e., jet mass, n-subjettiness, etc.). We shed light on limitations, and provide a novel empirical validation of image quality and validity of GAN-produced simulations of the natural world. This work provides a base for further explorations of GANs for use in faster simulation in High Energy Particle Physics..

0:00:00 Slide 1

0:00:29 Slide 2

0:00:56 Slide 3

0:01:32 Slide 4

0:02:12 Slide 5

0:03:04 Slide 6

0:05:10 Slide 7

0:05:38 Slide 8

0:06:34 Slide 9

0:07:08 Slide 10

0:09:30 Slide 11

0:10:54 Slide 12

0:11:34 Slide 13

0:12:10 Slide 14

0:13:22 Slide 15

0:13:55 Slide 16

0:14:44 Slide 17

0:15:35 Slide 18

0:16:03 Slide 19

0:17:22 Slide 20

0:18:07 Slide 21

0:19:25 Slide 22

0:20:03 Slide 23

0:20:11 Slide 24

0:20:35 Slide 25

0:21:17 Slide 26

0:22:00 Slide 27

0:23:02 Slide 28

0:24:06 Slide 29

0:24:40 Slide 30

0:24:45 Slide 31

0:24:49 Slide 32

0:25:22 Slide 33

0:25:27 Slide 34

0:27:27 Slide 35

0:30:13 Slide 36

0:30:30 Slide 37

0:32:39 Slide 38

0:32:43 Slide 39

0:32:48 Slide 40

0:32:52 Slide 41

0:33:14 Slide 42

0:33:19 Slide 43

0:34:12 Slide 44

0:34:17 Slide 45

## Lectures

1. [Application of Generative Adversarial Networks (GANs) to jet images](https://invisiblenetwork.ai/learn/cern/3017307/b788b8333e11), 37 min (CERN's player)