Choose timezone
Your profile timezone:
IMPRS-EPPC Hands-on Block Course: Fundamentals of Machine Learning
→
Europe/Berlin
Fritz-Haber-Institut
Fritz-Haber-Institut
Description
IMPRS-EPPC spring block course 2026
Fundamentals of Machine Learning - Hands-On Course
When: Mar 23 -26, 2026
Where: Fritz-Haber-Institut, Berlin
Directions
This course is primarily provided to members of the IMPRS-EPPC. Registration by invitation only.
Course requirements:
Own laptop, Python pre-installed (instructions)
Each participant is required to attend the full course Mo-Th, Python foundations and machine learning workshop.
Part 1: Python Foundations
Hands-on course led by T. Melson, N. Horlava, P. Coronica (MPCDF)
Mo/Tu, Mar 23/24, FHI Buiding P, Seminar Room P 2.05, 9:00-17:00
Link for materials
Course Description:
The course walks participants through the entire lifecycle of a Python project, from a single-script prototype to a fully version-controlled, tested, and publishable package ready to be developed collaboratively. Short, focused lectures alternate with practical, guided coding sessions to ensure that participants can immediately apply what they have just learned. While the hands-on exercises use Python, the core concepts (project structure, version control, testing strategies, CI/CD, documentation, etc.) are language-agnostic and transferable to other ecosystems.
Social event:
Tu, Mar 24, 17:00, Richard-Willstätter-Haus (FHI, building M)
Part 2: Machine Learning & Automation
Hands-on course, group work, lead by C. Scheurer (FHI Theory),
Mentored by G. Ducci, C. Kunkel, S. Rejman, M. Deimel, D. Balaz, S. Fürst, C. Pare, M. Vuijik, M. Kouyate (FHI Theory).
We/Th, Mar 25/26, FHI seminar room building M & other rooms (see schedule), 9:00-17:00
Course description:
The course will cover various classes of machine learning (ML) concepts as well as basics of lab-automation. We will give short intros to three classes of ML algorithms (e.g. NNs, symbolic regression, GPR, etc.) as well as fundamentals of lab automation.
The ML segment will cover typical application areas, simple math background of prototypical algorithms/models, and well-known toolboxes. The lab automation segment will focus on interfacing typical lab instruments with Python, implementing small use cases, and learning common protocols to interface with such hardware.
The students must then decide which of the two segments they want to get their hands on during group work. For the machine learning part, students will form groups of 6. For the lab automation part, students will form smaller groups of 2-3 people. Each team will be posed a simple ML problem for their method or a practical hardware task that they need to implement. TAs will provide support if needed.
On Thu afternoon, each team will present the findings on their chosen track to the other teams, discussing the different aspects of how they solved their problem and what they learned along the way.