# DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC

- Institution: CERN
- Department: LPCC Workshops
- Speaker: Serena Palazzo
- Year: 2019
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3016421)
- 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)

In this talk, I will present a Generative-Adversarial Network (GAN) based on convolutional neural networks that is used to simulate the production of pairs of jets at the LHC. The GAN is trained on events generated using MadGraph5 + Pythia8, and Delphes3 fast detector simulation. A number of kinematic distributions both at Monte Carlo truth level and after the detector simulation can be reproduced by the generator network with a very good level of agreement..

0:00:00 Slide 1

0:00:11 Slide 2

0:01:17 Slide 3

0:02:36 Slide 4

0:02:47 Slide 5

0:03:07 Slide 6

0:04:06 Slide 7

0:04:53 Slide 8

0:05:45 Slide 9

0:06:09 Slide 10

0:07:25 Slide 11

0:08:07 Slide 12

0:08:53 Slide 13

0:09:12 Slide 14

0:10:02 Slide 15

0:10:40 Slide 16

0:12:00 Slide 17

0:13:14 Slide 18

0:14:05 Slide 19

0:14:21 Slide 20

0:17:09 Slide 21

## Lectures

1. [DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC](https://invisiblenetwork.ai/learn/cern/3016421/a22531c36407), 21 min (CERN's player)