# Novelty Detection Meets Collider Physics

- Institution: CERN
- Department: LPCC Workshops
- Speaker: Ying-Ying Li
- Year: 2019
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3008995)
- 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)

Novelty detection is the machine learning task to recognize data, which belong to an unknown pattern. Complementary to supervised learning, it allows to analyze data model-independently. We demonstrate the potential role of novelty detection in collider physics, using autoencoder-based deep neural network. Explicitly, we develop a set of density-based novelty evaluators, which are sensitive to the clustering of unknown-pattern testing data or new-physics signal events, for the design of detection algorithms. We also explore the influence of the known-pattern data fluctuations, arising from non-signal regions, on detection sensitivity. Strategies to address it are proposed. The algorithms are applied to detecting fermionic di-top partner and resonant di-top productions at LHC, and exotic Higgs decays of two specific modes at a future e+e− collider. With parton-level analysis, we conclude that potentially the new-physics benchmarks can be recognized with high efficiency..

0:00:00 Slide 1

0:01:22 Slide 2

0:02:16 Slide 3

0:03:36 Slide 4

0:04:00 Slide 5

0:04:12 Slide 6

0:05:27 Slide 7

0:05:38 Slide 8

0:06:00 Slide 9

0:06:05 Slide 10

0:08:39 Slide 11

0:09:24 Slide 12

0:09:57 Slide 13

0:10:47 Slide 14

0:11:35 Slide 15

0:12:10 Slide 16

0:12:17 Slide 17

0:12:35 Slide 18

0:13:10 Slide 19

0:13:30 Slide 20

0:14:50 Slide 21

0:15:55 Slide 22

0:17:05 Slide 23

0:18:19 Slide 24

0:18:23 Slide 25

0:18:27 Slide 26

0:18:31 Slide 27

0:19:06 Slide 28

0:19:10 Slide 29

0:19:55 Slide 30

## Lectures

1. [Novelty Detection Meets Collider Physics](https://invisiblenetwork.ai/learn/cern/3008995/4896fab351b9), 23 min (CERN's player)