# An introduction to Bayesian neural networks and uncertainty quantification in neural networks

- Institution: CERN
- Department: Inverted CSC
- Speaker: Jacopo Talpini
- Year: 2023
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3000368)
- 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)

Over the past few years, many advances in the field of Deep Learning (DL) have been achieved and nowadays modern DL models are starting to be deployed in our everyday life. However, for many safety-critical applications, as long as scientific research fields, the quantification of the uncertainty of DL model predictions plays a crucial role. In this lecture, I will introduce the basics of Bayesian Neural Networks, how they can tackle the problem of estimating model uncertainty, and the most common techniques for generalizing this method to deep neural networks..

0:00:00 Slide 1

0:01:30 Slide 2

0:02:59 Slide 3

0:04:14 Slide 4

0:07:06 Slide 5

0:08:29 Slide 6

0:09:51 Slide 7

0:11:54 Slide 8

0:13:14 Slide 9

0:16:28 Slide 10

0:18:17 Slide 11

0:20:43 Slide 12

0:21:58 Slide 13

0:23:52 Slide 14

0:25:39 Slide 15

0:26:51 Slide 16

0:30:03 Slide 17

0:32:20 Slide 18

0:33:59 Slide 19

0:35:25 Slide 20

0:37:24 Slide 21

0:39:01 Slide 22

0:40:14 Slide 23

0:42:29 Slide 24

0:43:30 Slide 25

0:45:46 Slide 26

## Lectures

1. [An introduction to Bayesian neural networks and uncertainty quantification in neural networks](https://invisiblenetwork.ai/learn/cern/3000368/999d1377d876), 48 min (CERN's player)