# Deep Convolutional Networks for Event Reconstruction and Particle Tagging on NOvA and DUNE

- Institution: CERN
- Department: Machine Learning
- Speaker: Fernanda Psihas
- Year: 2017
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3025243)
- 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)

Deep Convolutional Neural Networks (CNNs) have been widely applied in computer vision to solve complex problems in image recognition and analysis. In recent years many efforts have emerged to extend the use of this technology to HEP applications, including the Convolutional Visual Network (CVN), our implementation for identification of neutrino events. In this presentation I will describe the core concepts of CNNs, the details of our particular implementation in the Caffe framework and our application to identify NOvA events. NOvA is a long baseline neutrino experiment whose main goal is the measurement of neutrino oscillations. This relies on the accurate identification and reconstruction of the neutrino flavor in the interactions we observe. In 2016 the NOvA experiment released results for the observation of oscillations in the ν μ → ν e channel, the first HEP result employing CNNs. I will also discuss our approach at event identification on NOvA as well as recent developments in the application of CNNs for particle tagging at NOvA, event identification at DUNE and other ongoing work..

0:00:00 Slide 1

0:00:56 Slide 2

0:01:47 Slide 3

0:02:32 Slide 4

0:03:16 Slide 5

0:04:09 Slide 6

0:04:36 Slide 7

0:05:30 Slide 8

0:06:57 Slide 9

0:08:20 Slide 10

0:09:16 Slide 11

0:10:12 Slide 12

0:10:50 Slide 13

0:11:46 Slide 14

0:13:07 Slide 15

0:14:10 Slide 16

0:15:07 Slide 17

0:15:32 Slide 18

0:16:38 Slide 19

0:16:43 Slide 20

0:17:13 Slide 21

0:18:16 Slide 22

0:18:44 Slide 23

0:19:14 Slide 24

0:20:34 Slide 25

0:21:56 Slide 26

0:23:06 Slide 27

0:24:00 Slide 28

0:25:10 Slide 29

0:26:07 Slide 30

0:27:09 Slide 31

0:29:09 Slide 32

0:29:15 Slide 33

0:29:19 Slide 34

0:29:23 Slide 35

0:29:28 Slide 36

0:29:39 Slide 37

0:29:44 Slide 38

0:29:50 Slide 39

0:31:52 Slide 40

0:31:56 Slide 41

## Lectures

1. [Deep Convolutional Networks for Event Reconstruction and Particle Tagging on NOvA and DUNE](https://invisiblenetwork.ai/learn/cern/3025243/7b03f7feeab1), 33 min (CERN's player)