Python for Machine LearningModule description #41143 / Version 6
- 6 CP
- Written exam
- Graded
- Winter and summer semester
- English
This module description is not valid in the current semester (Winter semester 2026/27).
Current version (v7)
| Module / Version | #41143 / #6 |
|---|---|
| Validity | Summer semester 2026 – Summer semester 2026 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Müller, Klaus-Robert |
| Grading | Graded |
| Exam format | Written exam |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Softwaretechnik und Theoretische Informatik |
| Academic chair | 34352000 FG Maschinelles Lernen |
Contact
| Office | FR 6-1 |
|---|---|
| Contact person | Wolff, Jannik |
| E-mail address | pyml@ml.tu-berlin.de |
| Website | https://web.ml.tu-berlin.de/teaching/courses/ |
Learning outcomes
Students demonstrate a strong conceptual understanding of Python, including core principles such as syntax, idioms, advanced functional and object-oriented patterns, and the libraries introduced in the course. They can implement advanced machine-learning tasks, informed by a solid understanding of the underlying concepts. They can use standard programming tools, such as programming environments and debuggers.
Content
- Python syntax and idioms (example: list comprehensions and type handling)
- Advanced functional and object-oriented patterns (example: decorators or dunder methods)
- Libraries (example: acceleration frameworks such as NumPy or Torch)
- Implementation of machine learning tasks, which includes conceptually understanding the setting
- Usage of programming environments (example: Jupyter environment & debugger)
The exact content (e.g., the provided examples) may differ across semesters, e.g., based on recent developments.
- Advanced functional and object-oriented patterns (example: decorators or dunder methods)
- Libraries (example: acceleration frameworks such as NumPy or Torch)
- Implementation of machine learning tasks, which includes conceptually understanding the setting
- Usage of programming environments (example: Jupyter environment & debugger)
The exact content (e.g., the provided examples) may differ across semesters, e.g., based on recent developments.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Python for Machine Learning | Integrated course | Winter and summer semester | [en] | 4 | WS 2026/27 (2) ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (2)
Python for Machine Learning (Integrated course) 2
Workload and credit points
Python for Machine Learning (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Tutorials | 9 | 2 h | 18 h |
| Preparation for the exam | 1 | 45 h | 45 h |
| Lectures | 9 | 2 h | 18 h |
| Preparation/follow-up work for the tutorials (including homework) | 9 | 8 h | 72 h |
| Preparation/follow-up work for the lectures | 9 | 3 h | 27 h |
| 180 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
The module consists of approximately nine lectures and the equivalent of approximately nine tutorial sessions. Some weeks include homework exercises. Students usually complete the homework outside the tutorials, though tutorials can provide help.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Students should know basic programming principles in Python or any language of equal or lower abstraction (e.g., not R). We recommend installing a virtual Python environment before the course starts. Note that this can require substantial time on operating systems like Windows. Students should know basic mathematical principles, e.g., knowledge of linear algebra helps understand the implementation of complex tensor operations.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Written exam |
| Language | English |
| Duration/Extent | 120 minutes |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter and summer semester.
Maximum number of participants
The maximum capacity of participants is 150.
Registration procedures
The course website on ISIS describes the admission for a given semester. Students are encouraged to familiarize themselves with the admission procedure in time (ideally before the semester starts). Otherwise, they may be unable to participate in the module if they miss important admission deadlines. Note that parts of the ISIS course are sometimes available to guests (without a TU account).
The maximum number of participants is determined by the organizational and technical resources available in a given semester.
The maximum number of participants is determined by the organizational and technical resources available in a given semester.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
available
Recommended literature
No recommended literature given
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Computer Engineering Computer Engineering (M. Sc.) - StuPO 2015 | SS 2026 | Wahlpflicht Studiengebiet B › Kognitive Systeme / Cognitive Systems |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | SS 2026 | Studiengebiete › Kognitive Systeme / Cognitive Systems |
| Digital Media and Technology Digital Media and Technology (M. Sc.) - StuPO 2017 | SS 2026 | Wahlpflichtbereich › Technische Profilbereiche (A) › Profilbereich Mensch-Maschine-Interaktion |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering |
| Engineering Science StuPO 2020 | SS 2026 | 2.1 Numerik und Simulation › 2.1b Ergänzungsbereich |
| ICT Innovation ICT Innovation (M. Sc.) - StuPO 2020 | SS 2026 | Studienrichtungen › Major: Embedded Systems › Exit year: Embedded Systems › Exit year Electives: Embedded Systems |
| Information Systems Management (Wirtschaftsinformatik) Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017 | SS 2026 | Wahlpflichtbereich › Fachstudium Informatik › Data and Software Engineering |
| Media Technology Media Technology (M. Sc.) - StuPO 2022 | SS 2026 | Wahlpflichtbereich Profilbereiche › Profilbereich Mensch-Maschine-Interaktion |
Miscellaneous
If feasible, the exam is digital and takes place in person: Students write code in a programming environment (e.g., a Jupyter environment) and have access to a Python interpreter, documentation (via Python's standard library), and a simple Python debugger via the Python standard library. The environment usually entails additional programming frameworks, e.g., for implementing tensor operations. The exact setup will be specified on ISIS and might differ based on technical or other constraints.
The feasibility of a digital exam cannot be guaranteed and is constrained by technical resources and other resources. The fallback solution is either a written exam (pen and paper) or a hybrid solution (e.g., no access to a Python interpreter, but submitting answers via ISIS).
Please review the course website on ISIS for additional information.
The feasibility of a digital exam cannot be guaranteed and is constrained by technical resources and other resources. The fallback solution is either a written exam (pen and paper) or a hybrid solution (e.g., no access to a Python interpreter, but submitting answers via ISIS).
Please review the course website on ISIS for additional information.