Advanced Deep Learning for Physics (IN 2298)

Time, Place: | Thursday, 10:00-12:00, HS2 [Wednesday , 16:00-18:00 HS2] First lecture: Thursday, April 12, 2018 |
Materials: | moodle page |
Schedule: | Apr. 11 Wed, 16:15 lecture |
Exam: | tba |
Content
Deep learning algorithms for physical problems are a very active field of research. The group of Prof. Thuerey has published a series of papers in this area, in particular regarding Navier-Stokes problems and fluids. You can find a summary here: physics-based deep learning research.
This course targets the corresponding deep learning and physics modeling foundations.
Specifically, it targets deep learning techniques and numerical simulation
algorithms for materials such as fluids and deformable objects in the context
of computer animation. The lecture and exercises will all be in English. The following topics are discussed:
- Generative neural networks & temporal network architectures
- Physically-based animation, fluid modeling
- Discretizations, and partial differential equations
- Exercises to gain hands-on experience with CNN training and fluid simulation algorithms
Prerequisites
- Introduction to Deep Learning (Previously called: Deep Learning for Computer Vision)
- Computer Gaphics Fundamentals, and Game Physics highly recommended
Literature
Machine Learning
- Goodfellow, Bengio, Courville: Deep Learning, 2016. http://www.deeplearningbook.org
- M. Nielsen: Neural Networks and Deep Learning, 2016.http://neuralnetworksanddeeplearning.com/
Fluid Simulation
- R. Bridson, M. Mueller-Fischer: Fluid Simulation for Computer Graphics;http://www.cs.ubc.ca/~rbridson/fluidsimulation/fluids_notes.pdf
- Griebel, Dornseifer, Neunhoeffer: Numerical Simulation in Fluid Dynamics: A Practical Introduction, Soc for Industrial & Applied Math
General Background
- Introduction to Linear Algebra: Gilbert Strang, Wellesley-Cambridge Press
- Computer Animation: Algorithms and Techniques, Parent, Morgan Kaufmann
Research
If you're interested, you can also check out some of our previous work on deep learning algorithms for fluid flow. These papers demonstrate several ways of training physics-aware neural networks for different parts of Navier-Stokes solvers.
Lecture Slides
Will be made available on the moodle page.