Machine Learning and Physics
Prof. Fred Hamprecht
Modern physics (and many other fields) is now unthinkable without machine learning / AI. This course teaches
Physics of Machine Learning – the physical ideas inside ML: energy and force, temperature and thermal fluctuations, diffusion, symmetry
Machine Learning for Physics – the tools physicists use today, including honest error bars (uncertainty quantification), fast stand-ins for slow simulations (learned surrogates), generative models, and parameter estimation when only a simulator is available (simulation-based inference).
Exercises are an important element of the course. They are part pen-and-paper, part programming with AI coding assistants, where you verify and interpret what they produce.
Provisional Curriculum
- Introduction; principal component analysis
- Robust statistics; nonlinear dimension reduction (t-SNE, UMAP)
- Density estimation; mean shift
- Linear regression and inverse problems
- Regularized regression: ridge, lasso, compressed sensing
- Statistical decision theory; discriminant analysis
- Decision trees, random forests, cross-validation
- Kernel methods, Gaussian processes, Bayesian optimization
- Logistic regression, softmax, generalized linear models
- Multi-layer perceptrons; double descent
- Training neural networks I: architecture, losses, regularization, normalization
- Training neural networks II: SGD, Adam, backpropagation
- Uncertainty quantification and calibration
- Convolutional networks
- Physics-informed neural networks, neural operators, PDE foundation models
- Representation learning: autoencoders and self-supervised learning
- Graph neural networks
- Attention and transformers
- Large language models
- AI safety, alignment, interpretability
- Diffusion and score-based models
- Normalizing flows, neural ODEs, flow matching
- Simulation-based inference
- Equivariant message-passing networks
- Molecular machine learning
- Q&A
Where and when
The lectures take place on Tuesdays and Thursdays from 9h15 until 11h00 in Großer Hörsaal, Philosophenweg 12. The first lecture is on Tuesday, 13 October 2026.
The tutorials start with a tooling session in the first week of the semester. Unless you are familiar with Python, Git, VS Code and AI coding agents, please take part to help you solve the computational exercises.
FAQ
Q: Do I need prior knowledge in machine learning?
A: No.
Q: I just want to learn the basics. Is this the right course?
A: The course has a steep learning curve and entails significant workload. If you only want to cover the basics, please check for slower-paced alternatives such as the “Machine Learning Essentials”.
Q: Is this course about deep learning?
A: Neural networks will play an important role; but this course is more about principles. While we will discuss architectural elements such as transformers, this course is not a detailed review of the latest architectures.
Q: Will this course be repeated next year?
A: Yes, like every MSc core course.
Q: Is this course open for students from other faculties?
A: Yes, but the last fifth in particular will require substantial effort if you come from outside physics.
Q: Is there a text book?
A: The course does not follow any single textbook, but the following are good sources: Hastie, Tibshirani, Friedman: The Elements of Statistical Learning; Bishop and Bishop: Deep Learning: Foundations and Concepts; Prince: Understanding Deep Learning; and, for the lectures on diffusion and flows, Holderrieth and Erives: An Introduction to Flow Matching and Diffusion Models.
Q: Exam modalities?
A: Admission to the written exam requires deliverables during the semester. Details will be discussed in week two.