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

Mathematical Foundations of Machine Learning IIModule description #20845 / Version 1

← Module page Deutsche Fassung
This module description is not valid in the current semester (Winter semester 2026/27). Current version (v2)
Module / Version#20845 / #1
ValiditySummer semester 2023 – Summer semester 2023
Available language(s)German
Credit points10
Person responsible for the moduleKreusler, Hans-Christian
GradingGraded
Exam formatOral exam
Language(s) of instructionGerman

Affiliation

FacultyFakultät II
InstituteInstitut für Mathematik
Academic chairNot specified

Contact

OfficeMA 5-4
Contact personGottschalk, Hanno
E-mail addressNot specified
WebsiteNot specified

Learning outcomes

Die Studierenden verstehen die Grundlagen des des Deep Learning und dessen Anwendungen im Bereich des Computergestützten Bildverstehens.
Sie können Problemstellung aus dem Bereich der Computer Vision geeigneten Modellen des Deep Learning zuordnen und Verstehen die Voraussetzungen, unter denen die Aufgabenstellung gelernt werden kann.

Content

Universelle Approximationsegenschaft tiefer neuronaler Netze
Adaptive Kapazitätsanpassung von tiefen neuronalen Netzen im Statistischen Lernen
Gefaltete und Gruppen-equivariante neuronale Netze
Mathematische Beschreibung moderner Netzarchitekturen mit Anwendung auf Computer Vision
Adversiales Lernen und generatives Lernen
Moderne Modelle des generativen Lernens

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Mathematische Grundlagen des Maschinellen Lernens IILecture Winter semester[de]4 ISIS
Mathematische Grundlagen des Maschinellen Lernens IIExercise Winter semester[de]2 ISIS

Courses in the course catalog

Courses created from the teaching units of this module.

Winter semester 2026/27 (3)

Mathematische Grundlagen des Maschinellen Lernens II (Lecture) 1

All groups of this course in the catalog

Mathematische Grundlagen des Maschinellen Lernens II (Exercise) 2

All groups of this course in the catalog

Workload and credit points

Mathematische Grundlagen des Maschinellen Lernens II (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance154 h60 h
Pre/post processing1510 h150 h
210 h

Mathematische Grundlagen des Maschinellen Lernens II (Exercise)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
30 h

Course-independent workload

Workload descriptionMultiplierHoursTotal
Prüfungsvorbereitung160 h60 h
60 h

The workload of the module adds up to 300 hours. The module therefore comprises 10 credit points.

Description of teaching and learning methods

Vorlesungen, Übungen

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

dringend empfohlen: Wahrscheinlichkeitstheorie I, Mathematische Grundlagen des Maschinellen Lernens I

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingGraded
Exam formatOral exam
LanguageGerman

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 semester.

Maximum number of participants

This module is not limited to a number of students.

Registration procedures

Standard.

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

unavailable

Recommended literature

  • Shalev-Shwartz, Shai, and Shai Ben-David. Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.
  • Van Handel, Ramon. Probability in high dimension. PRINCETON UNIV NJ, 2014.

Assigned programs

This module version is used in the following programs:

Program / program versionSemester(s)Curriculum component
Scientific Computing
Scientific Computing (M. Sc.) - StuPO 2022 (Beginn WS 2022/23)
SS 2023Wahlpflichtmodule › Mathematik

Miscellaneous

Not specified