Introduction to Machine Learning
This Module is offered by TUM Department of Electrical and Computer Engineering.
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
Module version of WS 2019/20 (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|
|WS 2019/20||SS 2019|
EI04016 is a semester module
in English language
at Bachelor’s level
which is offered in summer semester.
This Module is included in the following catalogues within the study programs in physics.
- Further Modules from Other Disciplines
|Total workload||Contact hours||Credits (ECTS)|
he course provides an introduction to concepts, methods, best practices, and theoretical foundations of standard machine learning algorithms. Topics covered include regression, classification, model selection and validation, kernels, nearest neighbor algorithms, clustering, decision trees, ensemble learning, empirical risk minimization and regularization.
Upon successful completion of the module students know the standard machine learning algorithms, how and when to apply those algorithms, their comparative strengths and weaknesses, and how to critically evaluate their performance. Students are able to (i) apply basic machine learning methods to build predictive models or perform exploratory analysis, (ii) properly tune, select and validate machine learning models, (iii) interpret their results, and (iv) understand their limits.
Analysis 1-3, Einführung in die Statistik oder Wahrscheinlichkeitsrechnung
Courses and Schedule
Learning and Teaching Methods
The foundations of machine learning and basic machine learning algorithms are introduced and explained during lectures, mostly on the board, but also by showing coding examples and running the algorithms on simple example data during the lectures. In each lecture, there will be brief (1-5 minute) exercised, typically posed as a question that the students will discuss in groups of two or three. Exercises with both theory and coding problems are handed out every second week, and whenever a new exercise is handed out, solutions for the previous one are distributed. The exercises allow the students to gain a deeper understanding of the methods by mathematically deriving properties about them, and by applying them on real data. The discussion session has an interactive format in that it is a forum for asking specific questions about the exercises and the methods introduced in the lectures, and discussing certain problems or parts of the lecture in more detail on the board, but only on request by the students during the discussion session.
The material is presented on the boad, sometimes code and algorithms are shown with a projector. Lecture notes and exercises are distributed.
We do not follows a textbook, lecture notes will be distributed. Helpful references include: ``Elements of Statistical Learning'' by Hastie, Tibshirani & Friedman; ``Machine Learning'' by Tom Mitchell ; ``Foundation of Machine Learning'', by Mohri, Rostamizadeh, and Talwalkar; ``Understanding Machine Learning: From Theory to Algorithms'' by Shalev-Shwartz and Ben-David
Description of exams and course work
Students have to take a written exam of two hours duration. In the exam, the students will answer questions on machine learning theory and practice, solve problems on machine learning theory and algorithms. The exam test whether students understand and can apply standard algorithms for regression and classification. Lecture notes are permitted in the exam, but no computer will be needed or is allowed.
There is a possibility to take the exam in the following semester.