Event
Project Lab Machine Learning [SS212512500]
Type
internship (P)Präsenz/Online gemischt
Term
SS 2021SWS
3Language
Deutsch/EnglischAppointments
0Links
ILIASLecturers
Organisation
- Angewandte Technisch-Kognitive Systeme
Part of
- Brick Advanced Lab Informatics (Master) | Industrial Engineering and Management (M.Sc.)
- Brick Project Lab Machine Learning | Industrial Engineering and Management (M.Sc.)
- Brick Advanced Lab Informatics (Master) | Economics Engineering (M.Sc.)
- Brick Project Lab Machine Learning | Economics Engineering (M.Sc.)
- Brick Advanced Lab Informatics (Master) | Information Systems (M.Sc.)
- Brick Project Lab Machine Learning | Information Systems (M.Sc.)
- Brick Advanced Lab Informatics (Master) | Information Engineering and Management (M.Sc.)
- Brick Project Lab Machine Learning | Information Engineering and Management (M.Sc.)
- Brick Advanced Lab Informatics (Master) | Economathematics (M.Sc.)
- Brick Project Lab Machine Learning | Economathematics (M.Sc.)
Note
The lab is intended as a practical supplement to lectures such as "Machine Learning". The theoretical basics are applied in the lab course. The aim of the lab course is that the participants work together to design, develop and evaluate a subsystem from the field of robotics and cognitive systems using one or more procedures from the field of AI/ML.
In addition to the scientific objectives involved in the investigation and application of the methods, aspects of project-specific teamwork in research (from specification to presentation of the results) are also developed in this practical course.
The individual projects require the analysis of the task at hand, selection of suitable procedures, specification and implementation and evaluation of the approach taken. Finally, the chosen solution has to be documented and presented in a short presentation.
Learning objectives:
- Students can practically apply knowledge from the Machine Learning lecture in a selected field of current research in robotics or cognitive automobiles.
- Students master the analysis and solution of corresponding problems in a team.
- Students can evaluate, document and present their concepts and results.
Recommendations:
Attendance of the lecture machine learning, C/C++ knowledge, Python knowledge
Workload:
The workload of 4.5 credit points consists of the time spent in the lab for practical implementation of the selected solution, as well as the time spent on literature research and planning/specifying the proposed solution. In addition, a short report and a presentation of the work carried out will be prepared.