Information on individual educational components (ECTS-Course descriptions) per semester | |
Degree programme: | Master Computer Science |
Type of degree: | FH MasterĀ“s Degree Programme |
Full-time | |
Winter Semester 2023 | |
Course unit title | Fundamentals of Machine Learning |
Course unit code | 024913010502 |
Language of instruction | German |
Type of course unit (compulsory, optional) | Elective |
Semester when the course unit is delivered | Winter Semester 2023 |
Teaching hours per week | 2 |
Year of study | 2023 |
Level of course unit (e.g. first, second or third cycle) | Second Cycle (Master) |
Number of ECTS credits allocated | 3 |
Name of lecturer(s) | Sebastian HEGENBART |
Prerequisites and co-requisites |
Basics in statistics, probability theory and linear algebra.
|
Course content |
Learning from examples is not exclusively restricted to living things. In fact, it is nowadays the basic principle used in a huge number of exciting applications, which rely on algorithms that are no longer explicitly defined but use data to learn how to behave. In this course the principles of such algorithms and methods are covered:
The methods are implemented or applied by using python with frameworks such as scikit-learn, numpy and keras. |
Learning outcomes |
Students are able to
|
Planned learning activities and teaching methods |
Lectures and exercises in homework. |
Assessment methods and criteria |
Final exam (75%), evaluation of exercises (25%). For a positive grade, a minimum of 50% of the possible points must be achieved in each part of the examination. |
Comment |
None |
Recommended or required reading |
|
Mode of delivery (face-to-face, distance learning) |
Face-to-face event with recording of the lecture |
Winter Semester 2023 | go Top |