Lab "Machine Learning"


Basic Information
Lecturers: Gerhard Schmidt and members of the DSS chair
Room: KS2/Geb.G - PC-Labor
Language: English
Target group: Master students in electrical engineering and computer engineering
Prerequisites: Basic skills in Python
Registration procedure:

As you will be working in groups of up to three students, please mention your desired group members in your registration. If you do not mention any desired group members, you will be assigned based on the order of your registration. Your registration has to include the following information:

  • surname, first name
  • stu-mail address
  • matriculation number
  • first and surname of desired group members.

Please note, that the registration period starts on 01.03.2023 at 8:00 am and ends on 05.04.2023 at 11:59 pm. All applications before and after this registration period will not be taken into account.

Registration will be possible within the before mentioned time by sending an e-mail with your name and matriculation number to the following address: This email address is being protected from spambots. You need JavaScript enabled to view it..

The registration is binding. A deregistration is possible by sending a mail with your name and matriculation number to This email address is being protected from spambots. You need JavaScript enabled to view it. until, 05.04.2023 at 11:59 pm. All later cancellations of registration will be considered as having failed the lab.


First meeting: 11.04.2023 at 10:00 h

Final presentations: 04.07.2023 at 10:00



Within this lab you will use Phython, TensorFlow and other (Phython-based) tools to learn about pattern recogntion and machine learing. To achieve this we will use data bases that are freely available to perform classification and regression approaches. These approches will vary in terms of computational complexity - from simple decision trees to complex deep neural networks (plus several "stages" in between). Furthermore, we will look at different evalution strategies in order to assess the quality in terms of the processing structure being able to gereralize to "unseen" data (not beeing part of the training data).

The lab can be done without listening to the lecture Pattern Recogition and Machine Learning. However, it is recommended also to particpate there. In the lab we will focus on how to use the tools, without going deeply in the underlying mathematical structures. This is the objective of the before mentioned lecture.



We assume that you have access to a computer (preferably your own notbook) that is powerful enough to let Python, TensorFlow, etc. run and that you can configure according to your needs (administrator rights). Furthermore, you should have basic knowledge in Python.



Link Content
The lab document.
Materials for lab 1 - "Introduction to Python"
Materials for lab 2 - "Data Sets"
Materials for lab 3 - "Linear Discriminant Analysis"
Materials for lab 4 - "Independent Component Analysis"
Materials for lab 5 - "Autoencoders"
Materials for lab 7 - "Support Vector Machines"
Materials for lab 8 - "Convolutional Neural Networks"



Current evaluation Completed evaluations