The Deep Learning Lab is aiming to impart students knowledge in the fields of machine learning and pattern recognition by practical application of corresponding methods. Students learn to implement and configure classification algorithms, such as linear discriminant functions, support vector machines, and neural networks. Modern concepts and approaches, especially deep learning are also part of the experiments. To motivate subsequent self-study only free-to-use datasets as well as open-source software will be used. For the computational complex training algorithms students are provided access to powerful centralized GPU (Graphical Processing Unit) hardware.
The Deep Learning Lab is divided in three parts:
• First, the students work themselves through an introduction to the Python programming language and all required libraries for the later experiments to obtain some basic knowledge.
• Second, the students will work with certain machine learning methods which are introduced in the Pattern Recognition lecture.
• Third, - in the so-called Machine Learning Challenge - students are required to use their obtained knowledge in order to develop a machine learning system in a competition with the other participating groups. Therefore, the students will be provided with real data which might stem from real-world/industry applications.
To support the ability to work in a team the excercises and the Machine Learning Challenge will be conducted in groups of 3 students. The maximum amount of participants is limited to 30 students. If there are more registrations than places available, we will apply a random selection.
We recommend to have attended either the lecture Pattern Recognition during the winter term or a comparable lecture as a basis for this lab.
The results of the first and the second parts will be reviewed in a colloquium with the supervising assistant. The results of the Machine Learning Challenge will be presented by each group in a closing event.
Lecturer: Prof. Tim Fingscheidt
Assistants: Thomas Graave, Björn Möller
Laboratory (DLL Lab) (ET-NT-111):
Contact hours (SWS): 4h = 5 LPs
Time: individually
Location: R 316 CIP Pool IfN
Kickoff Date: see below
Language: German / English
The registration for the Deep Learning Lab 2025 takes place from January 27 to February 07, 2025.
Information on the kick-off event and StudIP link will follow here.
The registration for the Deep Learning Lab 2025 is open from 27.01.2025 till 07.02.2025. Confirmations and rejections will be send via e-mail.
To register for the Deep Learning Lab 2025, send an e-mail to Tanja Kaib (tanja.kaib(at)tu-braunschweig.de) with CC to Björn Möller (bjoern.moeller(at)tu-braunschweig.de) and Thomas Graave (thomas.graave(at)tu-braunschweig.de).
Admission is granted primarily on the basis of relevant prior practical knowledge in the field of neural networks, e.g., from the courses Pattern Recognition, Computer Lab Pattern Recognition or other relevant lectures / practical laboratories / work experience.
For registration it is mandatory to supply the following information:
- first name, last name
- matriculation number
- degree program (field of study, as well as bachelor or master program)
- e-mail-adress given by the university
- written documentation of prior knowledge, preferably with proof (proof of grades, certificates, etc.)
Group registrations (3 persons) are permitted in a bundled email, stating the information of all participants.
The maximum amount of participants is limited to 30 students.
For more information, please have a look at the following articles from the last years:
2023: https://magazin.tu-braunschweig.de/en/m-post/recognising-the-unknown/
2022: https://magazin.tu-braunschweig.de/en/m-post/machine-pattern-recognition-for-masters-students/
2021: https://magazin.tu-braunschweig.de/?post_type=kb_magazin&p=44172&preview=true
2020: https://magazin.tu-braunschweig.de/m-post/praxislabor-mit-perspektive/
2019: https://magazin.tu-braunschweig.de/m-post/kleidungsstuecke-erkennen-mit-kuenstlicher-intelligenz/
2018: https://magazin.tu-braunschweig.de/m-post/mit-echten-daten-neuronale-netze-trainieren/
