This website is no longer updated.

As of 1.10.2022, the Faculty of Physics has been merged into the TUM School of Natural Sciences with the website For more information read Conversion of Websites.

de | en

Machine Learning

Module IN2064

This Module is offered by TUM Department of Informatics.

This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.

Module version of SS 2015

There are historic module descriptions of this module. A module description is valid until replaced by a newer one.

Whether the module’s courses are offered during a specific semester is listed in the section Courses, Learning and Teaching Methods and Literature below.

available module versions
SS 2022SS 2015WS 2011/2

Basic Information

IN2064 is a semester module in English language at Master’s level which is offered in winter semester.

This Module is included in the following catalogues within the study programs in physics.

  • Catalogue of non-physics elective courses
Total workloadContact hoursCredits (ECTS)
240 h 90 h 8 CP

Content, Learning Outcome and Preconditions


kNN & k-means; linear classifiers; linear regression; Bayes: maximum likelihood and maximum a posteriori estimator, mixture of Gaussians, Hidden Markov Models, Expectation Maximization algorithm, nonlinear neural networks and backprop, Support Vector Machines, unsupervised learning

Learning Outcome

Getting familiar with the statistics of machine learning. Basic knowledge of essential learning algorithms. Skill to select, describe and derive appropriate algorithms given a certain problem. Competence to apply these in practical application.


MA0901 Linear Algebra for Informatics, MA0902 Analysis for Informatics, IN0018 Discrete Probability Theory

Courses, Learning and Teaching Methods and Literature

Courses and Schedule

VI 6 Machine Learning (IN2064) Bilos, M. Gao, N. Geisler, S. Gosch, L. Günnemann, S. … (insgesamt 7) Mon, 10:00–12:00, GALILEO Audimax
Tue, 12:00–14:00, GALILEO Audimax
Wed, 16:00–19:00, MI HS1
and singular or moved dates

Learning and Teaching Methods

Flipped Classroom Lecture on the topics: Probability theory; kNN; multivariate Gaussian; linear regression and classification; kernels; constrained optimization; SVM; GP; neural network; unsupervised learning; expectation maximization; learning theory.
Exercise hours on the above topics
Homework for self-study on the above topics.


Slides, videos


Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer, Berlin, New York, 2006.
David J. C. MacKay. Information theory, inference, and learning algorithms. Cambridge Univ. Press, 2008.
Kevin Murphy. Machine Learning: a Probabilistic Perspective. MIT Press. 2012.

Module Exam

Description of exams and course work

The examination is a written test of 120 minutes. In this exam, students should prove that they are able to select suitable learning algorithms for specific problems and that they understand the probabilistic basics.

Exam Repetition

The exam may be repeated at the end of the semester.

Top of page