Every winter semester
5 Credit points
For information on the duration of the modul, refer to the courses of study in which the module is used.
Non-official translation of the module descriptions. Only the German version is legally binding.
Participants learn concepts and methods for structuring and using machine learning methods for more complex tasks.
tasks. This includes learning architectures, active learning strategies and sequential learning with restrictions, such as delayed success feedback or only partial system observability.
system observability. In addition, the lecture provides an overview of the most important theoretical approaches to machine learning.
theoretical approaches to machine learning and their mutual relationships.
Building on the module "Neural Networks and Learning", the learning methods considered there are subjected to a more detailed theoretical examination - especially from a statistical point of view. Furthermore, various learning architectures, in particular committee methods and reinforcement learning, are discussed.
Competences, such as those acquired in modules 39-Inf-NN Introduction to Neural Networks
—
In some degree programmes, the module (partial) examination can also be "ungraded" at the student's discretion. A corresponding specification must be made before the module is taken; a subsequent change (graded - ungraded) is not possible. If the ungraded option is selected, it is not possible to use this module for a degree programme in which this module is taken into account in the overall grade calculation.
Module structure: 0-1 bPr, 0-1 uPr 1
In some degree programmes of the Faculty of Technology, the module examination can also be "ungraded" at the student's discretion (see explanations of the module elements and the respective subject-specific regulations). If the ungraded option is selected, it is not possible to use this module for a degree programme in which this module is taken into account in the overall grade calculation.
See below for explanations of this examination (graded examination option).
Portfolio of exercises that are set during the course (pass mark 50% of the achievable points, individual explanation of the solutions). The exercises in the portfolio are usually handed out weekly. Final oral examination (15-25 min.) on the contents of the lecture and tutorials (in connection with lecture/seminar) or alternatively two board presentations on previously selected exercises.
| Degree programme | Profile | Recommended start 3 | Duration | Mandatory option 4 |
|---|---|---|---|---|
| Data Science / Master of Science [FsB vom 06.04.2018 mit Änderungen vom 01.07.2019, 02.03.2020, 21.03.2023 und 10.12.2024] | Variante 1 | 1. o. 3. | one semester | Compulsory optional subject |
| Data Science / Master of Science [FsB vom 06.04.2018 mit Änderungen vom 01.07.2019, 02.03.2020, 21.03.2023 und 10.12.2024] | Variante 2 | 1. o. 3. | one semester | Compulsory optional subject |
| Intelligent Systems / Master of Science [FsB vom 27.07.2018 mit Änderung vom 04.06.2020] | 1. | one semester | Compulsory optional subject | |
| Intelligent Systems / Master of Science [FsB vom 17.12.2012 mit Änderungen vom 15.04.2013, 01.04.2014, 15.10.2014, 02.03.2015 und Berichtigung vom 17.11.2014] | 1. o. 3. | one semester | Compulsory optional subject | |
| Informatics for the Natural Sciences / Master of Science [FsB vom 30.09.2016 mit Berichtigung vom 10.01.2017 und Änderungen vom 15.09.2017, 02.05.2018, 04.06.2020 und 31.03.2023] | 1. o. 3. | one semester | Compulsory optional subject | |
| Informatics for the Natural Sciences / Master of Science [FsB vom 17.12.2012 mit Änderungen vom 15.04.2013, 01.04.2014, 15.10.2014, 02.03.2015, 01.12.2015 und Berichtigungen vom 01.04.2014, 17.11.2014 und 12.07.2017] | 1. o. 3. | one semester | Compulsory optional subject |
The system can perform an automatic check for completeness for this module.