Teaching format (Lehrformen): This course is given with the problem based learning concept. The students work in groups of about 5 on realistic problems that can be solved with unsupervised learning methods from machine learning. They develop hypotheses and strategies for a solution and identify what they need to learn in order to implement these. Thus the students will not only learn about machine learning but also soft skills.

Requirements: The mathematical level of the course is mixed but generally high, including calculus (functions, derivatives, integrals, differential equations, ...), linear algebra (vectors, matrices, inner product, orthogonal vectors, basis systems, ...), and a bit of probability theory (probabilities, probability densities, Bayes' theorem, ...). Programming is done in Python, thus the students should have a basic knowledge of that as well, or at least be fluent in another programming language.

Content (Inhalt): This course covers a variety of unsupervised methods from machine learning such as principal component analysis, independent component analysis, vector quantization, clustering, Bayesian theory and graphical models.

Exam (Prüfungsformen): As an exam prerequisite (Prüfungsvorleistung) participants have to structure and document their learning progress and contribution to the group work, including setting personal testable milestones. The course is concluded with a ca 20 min graded oral exam. The dates are set at the end of the semester.

Condition for granting the credit points (Voraussetzungen für die Vergabe von Kreditpunkten): Exam prerequisite and passed oral exam

Course Material: Please download all material you need until end of July, because beginning in August I prepare the new course and some links of the old course might break.