Basic Lecture
The interdisciplinary introductory lecture "Introduction to Machine Learning" is aimed at Bachelor and Master students from different disciplines with heterogeneous prior knowledge. The lecture gives an overview of the fundamental concepts and algorithms of Machine Learning and explains them with basic application examples.
Practical courses
During one- to two-week practical courses (hackatons), in small (possibly interdisciplinary) groups, students can work with supervision on more comprehensive ML and AI projects that are thematically motivated by current research questions and applications.
The practical courses are expected to be first offered in the winter semester 2023/24 following the lecture period.
Notebooks
In the library, you will find selected introductory examples in the form of didactically prepared Jupyter notebooks, which accompany and complement the basic lecture, as well as an ever-growing number of simple examples from various ML and AI application areas.
Data Science +
The competent application of ML and AI not only requires an understanding of the corresponding algorithms, but also requires skills in querying databases, collecting data from the Internet, and processing and visualizing data. This is essential, especially for larger data science projects or to qualify for jobs in industry. For this reason, the library also includes a collection of Jupyter notebooks, which enables these basic data science skills to be acquired quickly and efficiently through self-study.
Accompanying and supplementary materials
Mathematical basics
Didn't do much mathematics in your studies and your school knowledge is already a bit dusty? - No problem! In complement to the introductory lecture, we provide a compendium of the required tools, which repeats and expands the relevant school mathematics. The script will be made available to the participants in advance of the lecture via Learnweb.
Contact: Dr. Katrin Schmietendorf, katrin.schmietendorf@uni-muenster.de.
Set up ML pipelines with ease using PHOTONAI
PHOTONAI is a high-level Python API for designing and optimizing ML pipelines. It includes various preprocessing and learning algorithms from state-of-the-art toolboxes, diverse hyperparameter optimization strategies, extended pipeline functionalities, and much more. Click here to see the documentation.
IVV NWZ Self-study Course Data Science/Machine Learning
The self-study course focusses on the technical aspects of ML. It guides the students in a structured manner through a number of external video, audio, text and software resources, so that they will be able to self-study the topic of data science with a focus on ML. Topics include data handling and analysis, machine learning algorithms, and data science software packages and tools.
Contact: Dr. Martin Korth, dgd@uni-muenster.de.