Term
Summer (2. Sem.)

Credits
5 ECTS

Majors
Master A&R: Module AR-310
Master ETIT: Module ETIT-277
Master SES : Module 3-28

Language
Englisch

Content

• Fundamentals of Machine Learning
• Regression
• Gaussian Process Regression
• Artificial Neural Networks
• Recurrent Neural Networks & Transformers
• Deep Learning

Competencies

After successful completion of the module, students possess advanced knowledge of the theoretical foundations, methods, and current developments in machine learning. They are able to formally describe, analytically understand, and critically reflect on key model classes such as regression methods, Gaussian process models, neural networks, deep learning approaches (including recurrent architectures and transformers), and reinforcement learning techniques.

Students can abstract complex problem settings and independently select, combine, and implement suitable machine learning approaches. They are capable of designing application-specific models and learning procedures, developing training and optimization strategies, and systematically evaluating and interpreting their performance using appropriate metrics.

Furthermore, students are able to comparatively analyze different learning methods and make well-founded decisions regarding their application. They can assess the strengths, weaknesses, and limitations of data-driven approaches. Students are also able to independently study scientific literature, critically contextualize current research results, and use them as a basis for advanced development, research, or knowledge-transfer tasks.

In line with the qualifications framework at the master’s level, students additionally develop the ability to recognize societal, ethical, and legal implications of the use of machine learning and to incorporate these aspects into their technical evaluations.