Technical University Berlin

All engineering disciplines today employ machine learning for monitoring systems and fault detection, for data-based decision support as well as for leveraging new potentials in the environment of big data. This module teaches the fundamentals of standard machine learning techniques as well as their implementation using standard libraries in the Python programming language based on real-world engineering examples. It focuses on the complete data science process from data exploration over modeling to inference and production.

The course is an introduction to the geometry of the image formation process and how visual data is represented and manipulated in a computer. Students learn projective geometry, which helps model the perspective projection, and digital image processing. Topics include how to model the perspective operation that happens when a picture is taken (projective geometry, image formation process), how pictures (visual data) are represented and processed in a computer (digital image processing), how to find out the internal geometric parameters of a camera (camera calibration), and what applications camera technology has in robotics (stereopsis, visual odometry, AR/VR, etc.).

The course's goal is to enable participants to acquire and process digital images in technical applications in a context-aware manner. The course introduces the basics of digital image processing, the acquisition of images in computing environments, and the extraction of semantic contents from the images. The goal of the course is the exemplary coverage of an interdisciplinary breadth, not necessarily an in-depth treatment of a specific domain. Fundamentals like sensor calibration, feature detection (e.g. edge extraction), matching and classification are taught. Integrated practical exercises cover operating a camera from a single-board computer and using a smartphone camera in a computer vision setting. Furthermore, exemplary machine learning approaches are used for “understanding” the images acquired previously. Software to be developed make use of the OpenCV Python library.

In this course, students gain a fundamental understanding of the functioning of international energy markets and perform sound analyses on energy markets. Students learn about the national and international transport and consumption of the main energy sources. Topics also include external costs and steering instruments, insights into newest developments, and how to do cost accounting and capital budgeting with respect to energy economics. 

The course includes international hybrid workshops by lecturers of all partner countries on technologies and background information necessary to develop sustainable community-based projects. Topics include intercultural communication, PV training, CO2compensation, household biogas plants, clean cooking, biogas, social business; international student hybrid working groups developing CO2compensation projects for climate and SDGs tackling the needs of the local partner communities together with the partner NGOs; practical Service elements contributing to the success of the project for the partner community and to the climate action (including, e.g., training sessions in schools, fundraising events, activities in waste management, organic gardening, tree planting); and research and innovation opportunities to deepen the development and application of sustainable technologies and methodologies.