This seminar focuses on advanced methodological aspects of machine learning and optimization in engineering applications, with an emphasis on hybrid approaches that combine data-driven learning with optimization techniques. Current research contributions are analyzed, critically assessed, and discussed, with a strong focus on modeling, algorithm design, and computational performance. Topics may include method-oriented projects in areas such as product design, industrial process optimization, or logistics systems.

Participants are required to independently study scientific literature, prepare a seminar paper, and present their findings in an oral presentation. Depending on the topic, a prototypical implementation and computational evaluation of the considered models or algorithms using modern software frameworks (e.g., Python-based ML libraries, optimization and simulation tools, or hybrid ML+optimization frameworks) is expected. All topics are designed to enable further development into a Master’s thesis.

Learning Objectives 

After successfully completing the seminar, students will be able to:

• independently evaluate hybrid ML and optimization approaches for engineering problems and implement them in prototypes.
• methodically review research literature,
• document their findings in writing, and present them in a scientific discussion.

The seminar will prepare students for writing a master's thesis in the field of Machine Learning and Optimization in Engineering.