After successful completion of the course, students are able to intimately understand the "tool" of machine learning and its application to problems in physics.

For a given problem in physics, students will be able to

• analyze whether Machine Learning is applicable,
• translate the problem into a suitable optimization problem,
• decide which learning algorithms are suitable for its solution
• program simple routines themselves as well as use libraries where applicable
• understand and verify the results of the learning procedure

The following topics are covered in the class, both theoretically and as applied to specific problems:

1. Simple optimization problems
2. Linear regression, Over-/underfitting, regularization
3. "The scientific method for machines"
4. Matrix completion, Feature classification
5. Non-linear models, Artificial Neuronal networks

This class will be held in English.

In the class methods of machine learning and applications thereof in physics are developed, and taught through computer exercises.

The class starts with a crash course into the Python programming language, which will then be used throughout.

Requirements for this class are:

1. weekly coding exercises, where you will appliy ML concepts to simple problems (70% of the grade)
2. a short oral exam, where you will have to demonstrate that you understood the concepts (30% of the grade).

Literature:

• M. P. Deisenroth, A. A. Faisal, and Cheng Soon Ong: Mathematics for Machine Learning, Cambridge University Press (2020)
• P. Mehta et. al: A high-bias, low-variance introduction to Machine Learning for physicists, Phys. Rep. 810, 1-124 (2019)
• G. James, D. Witten, T. Hastie and R. Tibshirani: An Introduction to Statistical Learning, Springer (2010)

• Linear Algebra
• Basic coding skills
• Recommended: intro quantum theory