384.185 Machine Learning
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2024S, VU, 3.0h, 4.5EC
TUWEL

Course evaluation

Properties

  • Semester hours: 3.0
  • Credits: 4.5
  • Type: VU Lecture and Exercise
  • Format: Presence

Learning outcomes

After successful completion of the course, students are able to...

- Understand a very broad collection of machine learning algorithms and problems

- determine when machine learning is feasible and can be meaningfully applied to specific challenges

- apply machine learning algorithms in their interested problems

- be qualified in doing researching in machine.

Subject of course

The lecture imparts understanding of methods from pattern classification and machine learning. The following topics are included: applications of machine learning, density estimation, regression techniques, pattern classifiers, probabilistic methods for classification, dimensionality reduction techniques, feature selection, statistical clustering, unsupervised learning, expectation-maximization algorithm, Validation, Markov process, hidden Markov models, Gaussian Processes, dynamic programming, reinforcement learning, neural networks.

Teaching methods

The contents of this lecture are presented with slides and on the blackboard. Exercises and tutorial courses, repeated calculations and problem solving will help develop deeper understanding for the matter. There is the possibility to gain practical experience through programming assignments.

Mode of examination

Written

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Fri09:00 - 11:0008.03.2024 - 28.06.2024EI 10 Fritz Paschke HS - UIW Vorlesung
Machine Learning - Single appointments
DayDateTimeLocationDescription
Fri08.03.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri15.03.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri22.03.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri12.04.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri19.04.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri26.04.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri03.05.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri17.05.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri24.05.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri31.05.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri07.06.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri14.06.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri21.06.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung
Fri28.06.202409:00 - 11:00EI 10 Fritz Paschke HS - UIW Vorlesung

Examination modalities

The evaluation will be based on a final (written) exam and programming assignment. The exam includes questions about theory, calculations, and practices, which covers the contents from lectures and exercise sessions.

Exams

DayTimeDateRoomMode of examinationApplication timeApplication modeExam
Thu18:00 - 20:0027.06.2024EI 7 Hörsaal - ETIT written06.05.2024 00:00 - 05.06.2024 17:00TISS384.185 VU Machine Learning Exam
Thu10:00 - 12:0005.09.2024EI 9 Hlawka HS - ETIT written01.06.2024 00:00 - 16.08.2024 23:00TISS384.185 VU Machine Learning Exam
Thu11:00 - 13:0026.06.2025EI 7 Hörsaal - ETIT written05.05.2025 00:00 - 04.06.2025 17:00TISS384.185 VU Machine Learning Exam

Course registration

Not necessary

Curricula

Study CodeObligationSemesterPrecon.Info
066 504 Master programme Embedded Systems Mandatory2. Semester
066 515 Automation and Robotic Systems Mandatory2. Semester

Literature

No lecture notes are available.

Previous knowledge

Basics of Linear Algebra, Probability and Statistics, Python programming

Continuative courses

  • 384.187 VU Robot Learning

Language

English