Skip to content

Machine Learning Course - Spring 2025

Repository for MAL1-S25 at VIA

Checkout the homepage!

Jump to Lesson Plan

Jump to Portfolios and Project

Course information

  • Course responsible: Associate Professor Richard Brooks, rib@via.dk
  • 5 ECTS (European Credit Transfer System), corresponding to 130 hours of work
  • Bachelor level course - the course is academically challenging working on problems independently.
  • Grade: 7-step scale
  • Recommended prerequisites: In "Sessions" in the left menu, a dedicated entry is made for prerequisites.

Lectures and course organization

  1. At the beginning of each session, there will be a short recap of the previous session.
  2. We then go through the exercises from the previous session.
  3. We will go through the theory of the current session.
  4. After classes, and before the next session, you will have to solve exercises from the current session.

This then loops back to (1) at the beginning of the next session.

There are no mandatory assignments, but it is highly recommended to work on the exercises for each session. No instruction is provided for the exercises so you will have to work on them on your own or form study groups.

Literature & Resources

Géron, Aurélien: Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, 3rd Edition. (the second edition will also do)

We highly recommend retrieving a copy of the book – it will also be the course book for the Deep Learning course in the Autumn.

Software

Make sure you install a working version of Jupyter Notebook and Python version 3.7 or higher. The easiest way to install Python and Jupyter is using Anaconda Distribution. You can choose whichever framework you want to work in as long as it can handle Jupyter Notebooks. Installing VS Code with a Jupyter Notebook extension seems to be a popular choice.

The course will be somewhat "Python-heavy" and during the course, it is expected that you can solve relatively complex machine learning problems in Python (in your assignments and project). It is expected that you are able to work in Python or learn to do so relatively fast.

Prerequisites

There are three main areas that are important when it comes to Machine Learning

  • Programming
  • Linear Algebra
  • Probability theory and statistics.

We assume that you have (1) covered! Linear Algebra knowledge you can obtain either by following our course (IT-ALI1) or you can see some suggestions below under Online Resource. The same goes for item (3). Now, it is possible to master machine learning without knowing anything about linear algebra or probability theory, but some topics will most likely be easier to comprehend if you have some background knowledge about the underlying mathematical foundation.

Online Resources

There are several Python-programming tutorials on YouTube, also ones that are data science / Machine Learning oriented. I recommend Alexander Ihler’s course Machine Learning and Data Mining.

For prerequisites, we have our own course here at VIA called Applied Linear Algebra. You can find an online version of the course at the course web page that also contains recordings from all sessions (from 2023).

In terms of probability theory and statistics, we have our own course here at VIA called Stochastic Modelling and Processing (IT-SMP1). You can find an online version of the course at the course web page that also contains recordings from all sessions (from 2021).

Historical Notes

Introduction to Machine Learning was first offered in the spring of 2018 and has been scheduled 1-2 times per year since then. The course responsible is Richard Brooks (RIB).

Grade Distribution 2023 (ordinary exam only)

Grade Count
12 13
10 7
7 15
4 7
02 5
00 6