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 2022 (current)

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 2022	SS 2015	WS 2011/2

Basic Information

IN2064 is a semester module in English language at Bachelor’s level and 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 workload	Contact hours	Credits (ECTS)
240 h	90 h	8 CP

Content, Learning Outcome and Preconditions

Content

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.

Preconditions

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

Courses, Learning and Teaching Methods and Literature

Courses and Schedule

WS 2022/3 WS 2021/2 WS 2020/1 WS 2019/20 WS 2018/9 WS 2017/8 WS 2016/7 WS 2015/6

Type	SWS	Title	Lecturer(s)	Dates	Links
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	eLearning

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.

Media

Slides, videos

Literature

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.

Current exam dates

Currently TUMonline lists the following exam dates. In addition to the general information above please refer to the current information given during the course.

Title
Time	Location	Info	Registration
Machine Learning
	0001 101 00.02.001