Navigation To modulepage
Display language

Mathematics of Machine Learning



#40894 / #3

Seit WS 2020/21

Fakultät IV


Institut für Telekommunikationssysteme

34331800 FG Netzwerk- und Informationstheorie

Stanczak, Slawomir

Reinhardt, Kerstin

POS-Nummer PORD-Nummer Modultitel
2347889 39602 Mathematics of Machine Learning

Learning Outcomes

After completeing the module the students will have a solid understanding of theoret- ical foundations of Machine Learning and will be able to develop, apply, and analyze the complexity of the resulting learning algorithms. Moreover, a special emphasis will be put on applications of Machine Learning in areas such as Signal Processing and Wireless Communications and the students will be able to theoretically analyze and algorithmically solve learning problems arising in these fields.


The learning content includes: • Learning Model • Learning via Uniform Convergence • Bias-Complexity Tradeoff • Stochastic Inequalities and Concentration of Measure • Suprema of empirical Processes • Vapnik- Chervonenkis Dimension (VC Dimension) • Nonuniform Learning • Runtime of Learning • Hilbert Spaces and Projection Methods • Kernel and Multi-Kernel Methods • Information Innovation • Regularization, Dimension Reduction and Compressive Sensing

Module Components


All Courses are mandatory.

Course Name Type Number Cycle Language SWS
Mathematical Introduction to Machine Learning VL WS No information 2
Theory and Algorithms of Machine Learning for Communication VL SS English 2

Workload and Credit Points

Mathematical Introduction to Machine Learning (VL):

Workload description Multiplier Hours Total
Attendance 15.0 2.0h 30.0h
Pre/post processing 15.0 4.0h 60.0h
90.0h(~3 LP)

Theory and Algorithms of Machine Learning for Communication (VL):

Workload description Multiplier Hours Total
Attendance 15.0 2.0h 30.0h
Pre/post processing 15.0 4.0h 60.0h
90.0h(~3 LP)
The Workload of the module sums up to 180.0 Hours. Therefore the module contains 6 Credits.

Description of Teaching and Learning Methods

The module consists of conventional frontal teaching in class, developing theoretical and mathematical concepts, exercises developed in class, in order to develop problem- solving skills and reinforce comprehension of the theory,

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Prerequisite for participation to courses are a mathematical background at the level of beginning MS students in Electrical Engineering (multivariate calculus, signals and systems, linear algebra and notions of matrix theory). The course is open to students enrolled in any MSc in EE CS, Mathematics and Physics.

Mandatory requirements for the module test application:

No information

Module completion



Type of exam

Oral exam




60 minutes

Duration of the Module

This module can be completed in 2 semesters.

Maximum Number of Participants

This module is not limited to a number of students.

Registration Procedures

Course teaching and organization (not module examination enrollment at Examination office/Prüfungsamt) is supported by an ISIS course. Registration details are provided at the beginning of the module.

Recommended reading, Lecture notes

Lecture notes

Availability:  unavailable

Electronical lecture notes

Availability:  available
Additional information:
Will be provided during the course


Recommended literature
P. Rigollet: Mathematics of Machine Learning, MIT Lecture Notes (online)
R. Vershynin: High-Dimensional Probability: An Introduction with Applications in Data Sciences (book in preparation, online)
S. Shalev-Schwartz and S. Ben-David: Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press 2014

Assigned Degree Programs

This module is used in the following Degree Programs (new System):

This moduleversion is used in the following modulelists:

Students of other degrees can participate in this module without capacity testing.


No information