Machine Learning in Engineering and Physical Sciences
The future importance of machine learning and data analytics is indisputable; it provides a means of creating added value from data. In the context of engineering, the data emanates from physical, chemical and mechanical systems and/or processes, which must obey the laws of physics. Consequently, a special branch of machine learning that incorporates models of these processes is required. Such model-based machine learning approaches enable the integration of dependencies, interactions and constraints which are essential for consistent, predictive and noise robust ML systems.
The summer school will give a general introduction to machine learning. This will include aspects such as: data preparation, representations for data, different ML architectures and quality assessment of learned solutions. There will be a focus on applications in the areas of: robotics, machine monitoring, and material science.
Schedule (tentative)
The week of this summer school will consist of morning lectures and afternoon hands-on workshops. It will cover foundational topics of machine learning and applications in various technical areas. We start with an optional get-together on Sunday evening and are also planning an outdoor excursion on Wednesday, which will conclude with dinner.
Lecturers
Martin Antenreiter
Peter Auer
Paul O'Leary
Lorenz Romaner
Elmar Rückert