# Classification of decays involving variable decay chains with convolutional architectures

- Institution: CERN
- Department: Machine Learning
- Speaker: Justin Tan
- Year: 2018
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3009901)
- 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)

Vidyo contribution

We present a technique to perform classification of decays that exhibit decay chains involving a variable number of particles, which include a broad class of $B$ meson decays sensitive to new physics. The utility of such decays as a probe of the Standard Model is dependent upon accurate determination of the decay rate, which is challenged by the combinatorial background arising in high-multiplicity decay modes. In our model, each particle in the decay event is represented as a fixed-dimensional vector of feature attributes, forming an $n \times k$ representation of the event, where $n$ is the number of particles in the event and $k$ is the dimensionality of the feature vector. A convolutional architecture is used to capture dependencies between the embedded particle representations and perform the final classification. The proposed model performs outperforms standard machine learning approaches based on Monte Carlo studies across a range of variable final-state decays with the Belle II detector..

0:00:00 Slide 1

0:00:25 Slide 2

0:01:42 Slide 3

0:03:07 Slide 4

0:04:00 Slide 5

0:05:12 Slide 6

0:06:38 Slide 7

0:06:54 Slide 8

0:07:59 Slide 9

0:10:09 Slide 10

0:11:19 Slide 11

0:13:12 Slide 12

0:14:03 Slide 13

0:14:12 Slide 14

0:15:41 Slide 15

0:16:43 Slide 16

0:18:41 Slide 17

0:21:04 Slide 18

0:21:35 Slide 19

0:21:54 Slide 20

0:22:19 Slide 21

0:22:49 Slide 22

0:23:37 Slide 23

0:23:43 Slide 24

0:23:47 Slide 25

0:25:20 Slide 26

0:27:48 Slide 27

## Lectures

1. [Classification of decays involving variable decay chains with convolutional architectures](https://invisiblenetwork.ai/learn/cern/3009901/ffbe10700efb), 31 min (CERN's player)