This course targets deep learning techniques and numerical simulation algorithms for materials such as fluids and deformable objects. In particular, this course will focus on advanced deep learning concepts such as generative models and time series prediction, with possible applications in the context of computer graphics or vision.
Course Structure
Lectures: Weekly, every Tuesday 16:15-17:45
in 5604.EG.011,
with video recordings available
Exercises/Homework: Weekly coding
assignments based on Jupyter notebooks and Python
Tutorial Support Sessions: Weekly, every
Friday (time TBA)
Lecture Content
Lecturer: Prof. Dr. Nils Thuerey
ECTS: 6
SWS: 4
Topics Covered:
- Introduction to Physics-based Deep Learning
- Neural Surrogates and Operators
- Physical Loss Terms
- Differentiable Physics
- Graph Neural Networks
- Diffusion Models and Score-based Methods
Lecture
| Date | Slides | Recording |
|---|---|---|
| April 16, 2025 | Lecture 01 | Recording |
| April 23, 2025 | Lecture 02 | Recording |
| April 30, 2025 | Lecture 03 | Recording |
Tutorials
| Week | Exercise |
|---|---|
| Week 1 | Exercise Sheet 1 |
| Week 2 | Exercise Sheet 2 |
| Week 3 | Exercise Sheet 3 |
| Week 4 | Exercise Sheet 4 |
Prerequisites
- Strong mathematical background: linear algebra, calculus, partial differential equations
- Previous knowledge of Python is required
- Basic understanding of physics simulations
- Machine Learning background is recommended
Course Team
Prof. Dr. Nils Thuerey
Course Instructor
Dr. Mario Lino
Course Instructor
Qiang Liu
Teaching Assistant
Benjamin Holzschuh
Lecture Support
Felix Koehler
Public Website