Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Machine Learning 1-X (9 LP)Module description #40834 / Version 3

← Module page Deutsche Fassung
This module description is not valid in the current semester (Winter semester 2026/27).
Module / Version#40834 / #3
ValidityWS 2019/20 – WS 2019/20
Available language(s)German
Credit points9
Person responsible for the moduleMüller, Klaus-Robert
GradingGraded
Exam formatWritten exam
Language(s) of instructionGerman

Affiliation

FacultyFakultät IV
InstituteInstitut für Softwaretechnik und Theoretische Informatik
Academic chair34352000 FG Maschinelles Lernen

Contact

OfficeMAR 4-1
Contact personMontavon, Gregoire
E-mail addressklaus-robert.mueller@tu-berlin.de
Websitehttps://wiki.ml.tu-berlin.de/wiki/

Learning outcomes

The students are able to independently apply methods from machine learning on new data. This includes methods for classification, regression, dimensionality reduction and clustering. Moreover, the module teaches the mathematical skills (probability theory, optimization theory) needed to extend and theoretical analyze machine learning methods.

Content

Probability theory, theory of estimation (e.g. Maximum likelihood, EM algorithm)

Methods from Machine Learning: Dimensionality reduction (PCA, ICA), Clustering, Supervised learning (e.g. Regression, LDA, SVM, Gaussian processes)

Depending on the elective: more detailed knowledge about specific machine learning problems, programming skills, or mathematical foundations.

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Maschinelles Lernen IIntegrated course0434 L 501 Winter semester–4 ISIS

Compulsory elective area

A selection of the following courses must be completed:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Algorithms for brain reading and writingSeminar Winter semester–2 ISIS
Bayesian LearningLecture343 L 8043 Winter semester–2 ISIS
Big Data: Skalierbares Maschinelles LernenSeminar Winter semester–2 ISIS
Big Data: Skalierbares Maschinelles LernenCourse Winter semester–2 ISIS
Boosting and Model AveragingSeminar Winter and summer semester–2 ISIS
Classical Topics in MLSeminar0434 L 588 Winter semester–2 ISIS
Deep Neural NetworksLecture Winter and summer semester–2 ISIS
Machine Learning and Data Management SystemsSeminar Winter and summer semester–2 ISIS
Machine Learning in the SciencesLecture Summer semester–2 ISIS
Mathematische Grundlagen für Maschinelles LernenCourse0434 L 545 Winter and summer semester–2 ISIS
Matlabprogrammierung für ML und DatenanlyseCourse0434 L 544 Winter and summer semester–2 ISIS
Pythonprogrammierung für ML und DatenanlyseCourse0434 L 543 Winter and summer semester–2 ISIS
Scientific applications in Machine LearningSeminar Winter and summer semester–2 ISIS

Courses in the course catalog

Courses created from the teaching units of this module.

Winter semester 2026/27 (5)

Maschinelles Lernen I (Integrated course) 4

All groups of this course in the catalog

Mathematische Grundlagen für Maschinelles Lernen (Course) 1

All groups of this course in the catalog

Workload and credit points

Maschinelles Lernen I (Integrated course)

Workload descriptionMultiplierHoursTotal
Präsenzzeit154 h60 h
Vor-/Nachbereitung158 h120 h
180 h

Algorithms for brain reading and writing (Seminar)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Bayesian Learning (Lecture)

Workload descriptionMultiplierHoursTotal
Präsenzzeit152 h30 h
Vor-/Nachbereitung154 h60 h
90 h

Big Data: Skalierbares Maschinelles Lernen (Seminar)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Big Data: Skalierbares Maschinelles Lernen (Course)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Boosting and Model Averaging (Seminar)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Classical Topics in ML (Seminar)

Workload descriptionMultiplierHoursTotal
Präsenzzeit152 h30 h
Vor-/Nachbereitung154 h60 h
90 h

Deep Neural Networks (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Machine Learning and Data Management Systems (Seminar)

Workload descriptionMultiplierHoursTotal
Präsenzzeit152 h30 h
Vor-/Nachbereitung154 h60 h
90 h

Machine Learning in the Sciences (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Mathematische Grundlagen für Maschinelles Lernen (Course)

Workload descriptionMultiplierHoursTotal
Präsenzzeit152 h30 h
Vor-/Nachbereitung154 h60 h
90 h

Matlabprogrammierung für ML und Datenanlyse (Course)

Workload descriptionMultiplierHoursTotal
Präsenzzeit152 h30 h
Vor-/Nachbereitung154 h60 h
90 h

Pythonprogrammierung für ML und Datenanlyse (Course)

Workload descriptionMultiplierHoursTotal
Präsenzzeit152 h30 h
Vor-/Nachbereitung154 h60 h
90 h

Scientific applications in Machine Learning (Seminar)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

The workload of the module adds up to 1350 hours. The module therefore comprises 9 credit points.

Description of teaching and learning methods

Die IV besteht aus einem Vorlesungsteil (Frontalunterricht vor allen Teilnehmer:innen zur Vermittlung des Stoffes) und einem Anteil praktischer Arbeit. Letztere besteht aus dem selbstständigen Bearbeiten von Übungsaufgaben.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Programmierkenntnisse, gute Grundlagen in Mathematik, insbesondere Lineare Algebra, Analysis, Wahrscheinlichkeitsrechnung. Dieses Modul ist auch für Bachelorstudierende geeignet.

Mandatory requirements for the module examination registration:

The examination requirements could not be retrieved.

Completion of the module

GradingGraded
Exam formatWritten exam
LanguageEnglish, German
Duration/Extent120 Minuten

Duration of the module

The following number of semesters is estimated for taking and completing the module: 2 semester(s).

This module can be started in the following semesters: Winter and summer semester.

Maximum number of participants

This module is not limited to a number of students.

Registration procedures

Keine.

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

unavailable

Recommended literature

No recommended literature given

Assigned programs

This module is not used in any program.

Miscellaneous

Die doppelte Anerkennung einzelner Lehrveranstaltungen aus bereits belegten Modulen ist ausgeschlossen.