# What is the machine learning.

- Institution: CERN
- Department: Machine Learning
- Speaker: Bryan Ostdiek
- Year: 2018
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3009512)
- 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)

Applications of machine learning tools to problems of physical interest are often criticized for producing sensitivity at the expense of transparency. In this talk, I explore a procedure for identifying combinations of variables -- aided by physical intuition -- that can discriminate signal from background. Weights are introduced to smooth away the features in a given variable(s). New networks are then trained on this modified data. Observed decreases in sensitivity diagnose the variable's discriminating power. Planing also allows the investigation of the linear versus non-linear nature of the boundaries between signal and background. I will demonstrate these features in both an easy to understand toy model and an idealized LHC resonance scenario..

0:00:00 Slide 1

0:00:34 Slide 2

0:01:27 Slide 3

0:01:56 Slide 4

0:02:18 Slide 5

0:03:20 Slide 6

0:04:00 Slide 7

0:04:11 Slide 8

0:04:40 Slide 9

0:06:24 Slide 10

0:07:24 Slide 11

0:07:46 Slide 12

0:08:02 Slide 13

0:08:09 Slide 14

0:08:19 Slide 15

0:09:38 Slide 16

0:09:48 Slide 17

0:11:27 Slide 18

0:12:33 Slide 19

0:13:04 Slide 20

0:13:29 Slide 21

0:14:03 Slide 22

0:14:29 Slide 23

0:14:37 Slide 24

0:16:06 Slide 25

0:16:12 Slide 26

0:16:33 Slide 27

0:21:05 Slide 28

0:22:06 Slide 29

## Lectures

1. [What is the machine learning.](https://invisiblenetwork.ai/learn/cern/3009512/ee774608bab6), 23 min (CERN's player)