Physics data analysis with machine learning

Machine learning tools have become indispensable for modern data analysis in both physics and industry. This course goes beyond introductory concepts and provides a comprehensive exploration of advanced data analysis and machine learning techniques.

We build upon the course Machine Learning for Physicists and Astronomers (FK7068) and cover both classical methods and modern deep learning approaches tailored for parameter inference and signal reconstruction. Topics such as generative modeling, simulation-based inference, acceleration of physics simulations through deep learning surrogates, anomaly detection, explainable AI, and physics-informed AI are presented. The course emphasizes practical applications by providing real-world scenarios relevant to cosmology, particle and astroparticle physics, through computer-based labs and leverages popular software libraries and publicly available datasets.

This is an advanced course given during the daytime.


Teaching Format

The course consists of both lectures and exercises.
 


Assessment

Examination takes place through written and oral examination. 


The schedule will be available no later than one month before the start of the course. We do not recommend print-outs as changes can occur. At the start of the course, your department will advise where you can find your schedule during the course.


Note that the course literature can be changed up to two months before the start of the course.


Course reports are displayed for the three most recent course instances.








Academic advisor at the Department of Physics: studievagledare@fysik.su.se

Student office: studentexp@fysik.su.se

Cookie settings

By allowing third-party services, you accept their cookies and the use of tracking technologies necessary for them to function properly.