183.605 Machine Learning for Visual Computing
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2022W, VU, 3.0h, 4.5EC


  • Semester hours: 3.0
  • Credits: 4.5
  • Type: VU Lecture and Exercise
  • LectureTube course
  • Format: Hybrid

Learning outcomes

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

  • choose suitable methods for a given problem
  • employ suitable technologies, software-tools and standards for the solution of a given problem
  • understand principles of machine learning

Subject of course

This introductory course teaches the basics of machine learning using computer vision examples. It focuses on a few key areas, on the basis of which the essential laws of machine learning are taught. Students gain a deeper understanding of the methods through independent implementation of the models in the laboratory exercise. The key areas are linear models with fixed basis functions and their kernel extensions as well as optimization methods in supervised and unsupervised learning scenarios. Models with adaptive basis functions and neural networks are introduced. The basic laws that are also dealt with in the exercises are: curse of dimensionality, bias-variance tradeoff and theoretical bounds on the generalization error and the relation to modelcomplexity. We will highlight aspects and challenges of learning from high dimensional data such as images.

In detail, the lecture deals with:

  • linear models for regression and classification (Perceptron, linear basis function models, polynomial and radial basis functions, historical overview), applications in computer vision
  • pre-processing, feature selection, feature engineering
  • neural networks
  • error functions and optimization (e.g., pseudo-inverse, gradient descent, newton method)
  • model complexity, regularization, model selection, VC dimension 
  • kernel methods: duality, sparsity, support vector machine
  • principal component analysis (linear encoder) and Hebbian rule
  • Bayesian view of the above models, Bayesian regression
  • Gaussian processes for regression
  • clustering and vector quantization, latent variables (e.g., k-means)
  • overview of deep learning models 










Teaching methods

An in-depth understanding of the key methodologies is tought by implementing basic classification and regression methods, enhancing them and evaluating them using image data.   Methods are:  

  • Lecture
  • implementation of methods discussed in the lecture using textual instructions
  • carrying out experiments using the implemented methods
  • documentation including decription and interpretation of results
  • oral feedback during assignment interviews

Mode of examination


Additional information

ECTS Breakdown:

4.5 ECTS = 112.5 hours
30     lecture time
70     2 assignments (including studying machine learning principles, 
       reading documents and literature, 
implementation of learning algorithms and writing documentation)
2.5    2 interviews (including preparation time)
10     written exam incl. preparation time    



Course dates

Fri11:00 - 13:0007.10.2022 - 20.01.2023EI 5 Hochenegg HS Lecture
Machine Learning for Visual Computing - Single appointments
Fri07.10.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri14.10.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri21.10.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri28.10.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri04.11.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri11.11.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri18.11.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri25.11.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri02.12.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri09.12.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri16.12.202211:00 - 13:00EI 5 Hochenegg HS Lecture
Fri13.01.202311:00 - 13:00EI 5 Hochenegg HS Lecture
Fri20.01.202311:00 - 13:00EI 5 Hochenegg HS Lecture

Examination modalities

  • two assignments
  • two assignment interviews
  • one written exam


DayTimeDateRoomMode of examinationApplication timeApplication modeExam
Wed17:00 - 19:0006.03.2024FAV Hörsaal 1 Helmut Veith - INF written21.02.2024 08:00 - 04.03.2024 12:00TISSMLVC written exam (first alternate date)
Wed15:00 - 17:0015.05.2024EI 9 Hlawka HS - ETIT written30.04.2024 08:00 - 14.05.2024 12:00TISSMLVC written exam (second alternate date)
Wed17:00 - 19:0012.06.2024FAV Hörsaal 1 Helmut Veith - INF written28.05.2024 08:00 - 11.06.2024 12:00TISSMLVC written exam (third alternate date)

Course registration

Begin End Deregistration end
26.09.2022 09:00 19.10.2022 23:59 31.10.2022 23:59

Registration modalities

Please register for the course in TISS. After registration you can team up as a group of 3 students in TUWEL.


Study CodeObligationSemesterPrecon.Info
066 453 Biomedical Engineering Not specified
066 645 Data Science Not specified
066 926 Business Informatics Not specified
066 932 Visual Computing Mandatory2. Semester
066 936 Medical Informatics Mandatory elective


No lecture notes are available.

Previous knowledge

Knowledge of linear algebra and probability theory

Continuative courses