Machine Learning between function spaces: Neural Operators
- Research topic/area
- ML
- Type of thesis
- Master
- Start time
- 02.11.2026
- Application deadline
- 23.10.2026
- Duration of the thesis
- 3-6 Monate
Description
When considering machine learning on e.g. image data, it is alway necessary to discretise the input and output. E.g. we view image data as 1024x1024 grid of values instead of the continuous space beneath it [0, 1]^2. The objective of neural operators is to design machine learning architectures that can cope with different discretizations of the same input space.Goals of the thesis could be:1. understand the theory behind neural operators and current architectures,2. implement such a machine learning model, and3. perform a benchmark on a suitable dataset to compare architectures.Some introductory literature can be found at:https://arxiv.org/abs/2304.13221https://arxiv.org/abs/2010.08895
Requirement
- Requirements for students
-
- - python
- - machine learning
- - math
- Faculty departments
-
- Economic & law sciences
Business management
- Economic & law sciences
Supervision
- Title, first name, last name
- Leonard Vetter
- Organizational unit
- KIT, IOR
- Email address
- vetter@kit.edu
- Link to personal homepage/personal page
- Website
Application via email
- Application documents
-
- Curriculum vitae
- Grade transcript
- Certificate of enrollment
E-Mail Address for application
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an vetter@kit.edu
Back