# Uncertainty Quantification in PDF Determinations: a Machine Learning Adventure

- Institution: CERN
- Speaker: Luigi Del Debbio
- Year: 2026
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3020600)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

Precise and accurate theoretical predictions are a fundamental ingredient in order to exploit the full potential of the wealth of data from the LHC experiments. In this context, it is particularly important to have a robust determination of the uncertainties on the current determinations of Parton Distribution Functions (PDFs). The NNPDF collaboration has pioneered the usage of Machine Learning (ML) techniques in order to extract PDFs from a finite set of data, a typical example of an inverse problem. In this talk we introduce a framework to analyse the training of Neural Networks, present its application to the PDFs determination, and discuss future research directions.

0:00:00 Slide 1

0:02:20 Slide 2

0:02:43 Slide 3

0:05:11 Slide 4

0:05:54 Slide 5

0:06:18 Slide 6

0:08:08 Slide 7

0:08:52 Slide 8

0:10:27 Slide 9

0:11:43 Slide 10

0:14:34 Slide 11

0:16:45 Slide 12

0:18:11 Slide 13

0:20:07 Slide 14

0:20:34 Slide 15

0:21:06 Slide 16

0:21:39 Slide 17

0:23:41 Slide 18

0:24:45 Slide 19

0:25:27 Slide 20

0:27:42 Slide 21

0:33:03 Slide 22

0:33:17 Slide 23

0:34:46 Slide 24

0:36:05 Slide 25

0:37:17 Slide 26

0:37:45 Slide 27

0:39:55 Slide 28

0:42:31 Slide 29

0:44:00 Slide 30

0:46:25 Slide 31

0:47:05 Slide 32

0:49:35 Slide 33

0:51:37 Slide 34

0:54:41 Slide 35

0:57:19 Slide 36

1:00:08 Slide 37

1:00:24 Slide 38

1:01:19 Slide 39

1:03:35 Slide 40r>

## Lectures

1. [Uncertainty Quantification in PDF Determinations: a Machine Learning Adventure](https://invisiblenetwork.ai/learn/cern/3020600/f161c3126b03), 1 h 5 min (CERN's player)