Hands on Machine Learning

Andrea Klaura
Art and Technology, Coding Lab
2023S, Vorlesung und Übungen (VU), 2.0 ECTS, 2.0 semester hours, course number S04593


Ongoing course documentation: https://tantemalkah.at/2023/machine-learning/

This course is the practical/experimental companion to Clemens Apprich's seminar on the theory and history of Machine Learning. While it is not a formal requirement to also attend this other course, we highly recommend to jointly attend both of those two courses.

Learning goals:

After completion of this course you will be able to

* Set up and train simple machine learning models based on the Python programming language* Analyse data sets in terms of their usability for machine learning processes
* Pre-process and prepare data sets for their use in training machine learning models
* Critically reflect on the techno-social and infrastructural requirements for successful machine learning applications
* Evaluate and assess machine learning processes in terms of risk and ethical considerations

Course outline:

The course features three major parts we will focus on:

1. Intro & linear regression models: in the first weeks of the course we will familiarise ourselves with the basic setup and the scripting basics we need to create and experiment with simple linear regression models with Python on your own computing device.
2. Recommender systems: after we gained some familiarity with creating and working on linear regression models, we focus on recommender systems and creating and experimenting with machine learning models that can be used in recommender systems
3. Project work & open experimentation: the final weeks of the course aim at defining specific (prototype) projects, which the attendees will work on either individually or in groups, as part of their final exercise in this course


There is no explicit requirement to attend this course. Pre-existing mathematical and programming knowledge will help, but the course is designed to teach you all the technological skills from scratch. A familiarity with your own device (see BYOD policy below) and how to install software should be given.

ECTS breakdown:

2 ECTS = 50 hours

* 18 hours: scheduled teaching sessions
* 12 hours: exercises alongside the teaching sessions
* 20 hours: final project

Examination Modalities

Grading will be based on:

* 30%: Attendance & active participation
* 30%: Coding exercises
* 40%: Final project


BYOD policy:

Please bring your own device (ideally a laptop computer), to get most out of the course, as part of the course sessions will facilitate hands-on exercises in coding. In case you do not have a laptop or cannot bring one, it is possible to team up with another person with laptop. In that case you will have to do more work outside the course, in order to submit the exercises.

Key Words

machine learning, AI, coding, programming, python, tensor flow, linear regression, recommender systems


02 March 2023, 12:30–14:00 Seminar Room 33 (preliminary discussion)
09 March 2023, 12:30–14:00 Seminar Room 33 , "Setup & Python basics"
16 March 2023, 12:30–14:00 Seminar Room 33 , "Python basics recap, loops, functions"
23 March 2023, 12:30–14:00 Seminar Room 33 , "Reading and analysing .csv data sets"
30 March 2023, 12:30–14:00 Seminar Room 33 , "Pretty Plotting Pandas"
20 April 2023, 12:30–14:00 Seminar Room 33 , "Perceptrons in Python Practice"
27 April 2023, 12:30–14:00 Seminar Room 33 , "Getting into linear regression"
04 May 2023, 12:30–14:00 Seminar Room 33 , "Linear regression continued"
11 May 2023, 12:30–14:00 Seminar Room 33 , "Excursion to the E-Day"
25 May 2023, 12:30–14:00 Seminar Room 33
01 June 2023, 12:30–14:00 Seminar Room 33 (guest lecture: Sandra Stuhlhofer)
22 June 2023, 12:30–14:00 Conference Room 17

Course Enrolment

From 01 February 2023, 05:42 to 02 March 2023, 12:23
Via online registration

Transformation Studies. Art x Science (Bachelor): Focus! Transformation Areas: Digital Transformation 162/040.10

TransArts - Transdisciplinary Arts (Bachelor): Artistic and art technology foundations: Artistic and art technology foundations 180/002.01

Cross-Disciplinary Strategies (Master): Study Areas 1-3: Study Area 2: Science and Technology 569/020.02

Cross-Disciplinary Strategies (Master): Elective Field: Free Electives 569/080.80

Fine Arts (2. Section): Artistic Practice in Technical Context: Workshops 605/203.10

Fine Arts (2. Section): Artistic Practice in Technical Context: Free Electives out of Artistic Practice in Technical Context 605/203.80

Cross-Disciplinary Strategies (Bachelor): Science and Technology: Deepening / Application 700/002.20

Co-registration: not possible

Attending individual courses: not possible