1. Modulverzeichnis (MTS)
  2. Module
  3. Modulbeschreibung anzeigen

Python für Maschinelles Lernen

Zur Modulseite PDF generieren

#41143 / #5

Seit SoSe 2025

English

Python for Machine Learning
Python für Maschinelles Lernen

6

Müller, Klaus-Robert

Benotet

Schriftliche Prüfung

English

Zugehörigkeit


Fakultät IV

Institut für Softwaretechnik und Theoretische Informatik

34352000 FG Maschinelles Lernen

Keine Angabe

Kontakt


MAR 4-1

Wolff, Jannik

pyml@ml.tu-berlin.de

https://web.ml.tu-berlin.de/teaching/courses/

Lernergebnisse

The students have a deep theoretical understanding of Python programming, which they can apply autonomously using standard programming tools such as Jupyter notebooks and a debugger. Specifically, Students understand general principles underlying Python programming, e.g., Python syntax and advanced paradigms of functional and object-oriented programming. They can apply these skills to advanced data science and machine learning tasks. This includes efficiently and compactly implementing complex tensor operations and implementing visualization methods.

Lehrinhalte

The module briefly motivates Python by contrasting it to other programming paradigms (e.g., Julia or C). The module introduces Python-specific programming principles, e.g., duck typing or idiomatic constructs (“Pythonic” syntax) such as generator comprehensions. Students implement visualization code primarily using the framework Matplotlib. The module teaches the application of the learned programming skills to machine learning (ML) problems, which includes conceptually understanding exemplary ML tasks. For example, the module teaches the implementation of complex tensor operations (often relevant in machine learning) using acceleration frameworks (such as NumPy or PyTorch) that ensure compact syntax and efficient computation. The module teaches the use of programming environments such as Jupyter notebooks and tools like debuggers, which can also be used during the exam (assuming a digital exam is feasible in a given semester).

Modulbestandteile

Compulsory area

Die folgenden Veranstaltungen sind für das Modul obligatorisch:

LehrveranstaltungenArtNummerTurnusSpracheSWS ISIS VVZ
Python for Machine LearningIVWiSe/SoSeen4
ISIS-Kurssuche nach Veranstaltungen des Moduls

Arbeitsaufwand und Leistungspunkte

Python for Machine Learning (IV):

AufwandbeschreibungMultiplikatorStundenGesamt
Tutorials9.02.0h18.0h
Preparation for the exam1.045.0h45.0h
Lectures9.02.0h18.0h
Preparation/follow-up work for the tutorials (including homework)9.08.0h72.0h
Preparation/follow-up work for the lectures9.03.0h27.0h
180.0h(~6 LP)
Der Aufwand des Moduls summiert sich zu 180.0 Stunden. Damit umfasst das Modul 6 Leistungspunkte.

Beschreibung der Lehr- und Lernformen

The module exhibits a hybrid format: On the one hand, the course instructors teach some of the content in person in a guided format. On the other hand, students learn to program autonomously and individually while establishing a sound theoretical understanding of programming paradigms and relevant machine-learning problems. Specifically, the module contains approximately nine lectures and the equivalent of nine tutorial sessions. Some weeks contain homework exercises. These must be done individually, although the tutorials provide help if necessary, and possible solutions are discussed after the homework deadline.

Voraussetzungen für die Teilnahme / Prüfung

Wünschenswerte Voraussetzungen für die Teilnahme an den Lehrveranstaltungen:

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.

Verpflichtende Voraussetzungen für die Modulprüfungsanmeldung:

Dieses Modul hat keine Prüfungsvoraussetzungen.

Abschluss des Moduls

Benotung

Benotet

Prüfungsform

Written exam

Sprache(n)

English

Dauer/Umfang

120 minutes

Dauer des Moduls

Für Belegung und Abschluss des Moduls ist folgende Semesteranzahl veranschlagt:
1 Semester.

Dieses Modul kann in folgenden Semestern begonnen werden:
Winter- und Sommersemester.

Maximale teilnehmende Personen

Die maximale Teilnehmerzahl beträgt 180.

Anmeldeformalitäten

The module's website (to be found at the website of the Machine Learning Group at TU Berlin) describes the admission formalities for a given semester in detail. Students are encouraged to inform themselves about the admission procedure on time (ideally before the semester starts). Otherwise, they may be unable to participate in the module when missing important admission deadlines. Students can only participate in this module if they have not(!) passed the elective “Python Programming for Machine Learning (PyML)” (3 CP). The PyML elective was discontinued after the winter term 2023/2024. The maximum number of participants is 180. If circumstances change, e.g., concerning the capacity of the digital examination facilities, the module’s capacity limit may be adjusted. A change in the number of participants for a given semester (if any) will be published on the module's website.

Literaturhinweise, Skripte

Skript in Papierform

Verfügbarkeit:  nicht verfügbar

 

Skript in elektronischer Form

Verfügbarkeit:  verfügbar

 

Literatur

Empfohlene Literatur
Keine empfohlene Literatur angegeben

Zugeordnete Studiengänge


Diese Modulversion wird in folgenden Studiengängen verwendet:

Studiengang / StuPOStuPOsVerwendungenErste VerwendungLetzte Verwendung
Computer Engineering (M. Sc.)14SoSe 2025SoSe 2025
Computer Science (Informatik) (M. Sc.)15SoSe 2025SoSe 2025
Elektrotechnik (M. Sc.)13SoSe 2025SoSe 2025
ICT Innovation (M. Sc.)12SoSe 2025SoSe 2025
Information Systems Management (Wirtschaftsinformatik) (M. Sc.)12SoSe 2025SoSe 2025
Medieninformatik (M. Sc.)12SoSe 2025SoSe 2025
Medientechnik (M. Sc.)14SoSe 2025SoSe 2025
Physikalische Ingenieurwissenschaft (M. Sc.)22SoSe 2025SoSe 2025

Sonstiges

If feasible, the exam is digital, where students write code in Jupyter notebooks and have access to a Python interpreter, documentation (via Python's standard library), and a simple Python debugger. In this case, the exam takes place in person, i.e., it is not an online exam. However, the feasibility of the digital exam concept cannot be guaranteed and is constrained by technical resources and other resources. The fallback solution is either a written exam (with pen and paper) or a hybrid solution (e.g., no access to a Python interpreter but submitting answers via ISIS). Students can bring an A4 sheet to the exam. They should check the course website for details on what this A4 sheet can entail. We recommend reading the course website on ISIS for additional information.