# Machine-learning in Calabi-Yau geometry

- Institution: CERN
- Department: Conferences, Workshops & Schools
- Speaker: Magdalena Larfors
- Year: 2024
- Language: English
- Subjects: Mathematics, Computer science
- Source: [CERN](https://videos.cern.ch/record/3011175)
- 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)

Calabi Yau (CY) manifolds are used ubiquitously in string theory. These spaces are central both to string phenomenology and formal developments. While CY manifolds can be constructed in large numbers, and much is known about their topological features, their geometry is still partly enigmatic. In particular, we lack an analytical expression for Ricci-flat metrics on CY n-folds for n>2. In this talk, I will review recent work on obtaining numerical approximations of CY metrics using machine learning, and how such metrics may be used string theory research..

0:00:00 Slide 1

0:01:13 Slide 2

0:02:33 Slide 3

0:04:16 Slide 4

0:05:33 Slide 5

0:06:42 Slide 6

0:09:25 Slide 7

0:12:28 Slide 8

0:13:59 Slide 9

0:15:28 Slide 10

0:16:41 Slide 11

0:19:18 Slide 12

0:20:25 Slide 13

0:21:49 Slide 14

0:24:10 Slide 15

0:27:45 Slide 16

## Lectures

1. [Machine-learning in Calabi-Yau geometry](https://invisiblenetwork.ai/learn/cern/3011175/bbb445b9d2fd), 30 min (CERN's player)