# Neural networks for the abstraction of the physical symmetries in the nature

- Institution: CERN
- Department: LPCC Workshops
- Speaker: Wonsang Cho
- Year: 2019
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3012035)
- 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)

Neural networks are so powerful universal approximator of complicated patterns in large-scale data, leading the explosive developments of AI in terms of deep learning. However, in many cases, usual neural networks are trained to possess poor level of abstraction, so that the model's predictability and generalizability can be quite unstable, depending on the quality and amount of the data used for training. In this presentation, we introduce a new neural network architecture which has improved capability of capturing the key features and the physical laws hidden in data, in a mathematically more robust and simpler way. We demonstrate the performance of the new architecture, with an application for high energy particle scattering processes at the LHC..

0:00:00 Slide 1

0:00:30 Slide 2

0:01:10 Slide 3

0:02:33 Slide 4

0:04:01 Slide 5

0:04:41 Slide 6

0:05:20 Slide 7

0:05:41 Slide 8

0:06:06 Slide 9

0:06:33 Slide 10

0:07:46 Slide 11

0:08:17 Slide 12

0:10:20 Slide 13

0:10:45 Slide 14

0:11:08 Slide 15

0:11:22 Slide 16

0:12:23 Slide 17

0:13:21 Slide 18

0:14:17 Slide 19

0:14:55 Slide 20

0:15:16 Slide 21

0:15:26 Slide 22

0:15:30 Slide 23

0:15:40 Slide 24

0:16:49 Slide 25

0:17:13 Slide 26

0:17:24 Slide 27

0:17:47 Slide 28

0:18:10 Slide 29

0:20:49 Slide 30

## Lectures

1. [Neural networks for the abstraction of the physical symmetries in the nature](https://invisiblenetwork.ai/learn/cern/3012035/9ec35a9612b9), 22 min (CERN's player)