Machine Learning in Practice
Course infoSchedule
Course moduleNWI-IMC030
Credits (ECTS)6
CategoryMA (Master)
Language of instructionEnglish
Offered byRadboud University; Faculty of Science; Informatica en Informatiekunde;
PreviousNext 3
ir. N. Knyazev
Other course modules lecturer
dr. T.M. van Laarhoven
Other course modules lecturer
prof. dr. ir. D.A. van Leeuwen
Other course modules lecturer
Contactperson for the course
dr. H.R. Oosterhuis
Other course modules lecturer
dr. H.R. Oosterhuis
Other course modules lecturer
Academic year2023
KW3-KW4  (29/01/2024 to 31/08/2024)
Starting block
Course mode
Registration using OSIRISYes
Course open to students from other facultiesYes
Waiting listNo
Placement procedure-
At the end of this course, the student is able to 
  • reason and argue about what type of algorithms and efficient source code to be developed and applied when tackling real-life machine learning tasks;
  • understand the principles underlying effective machine learning methods;
  • use and adapt state-of-the-art machine learning algorithms to tackle a challenge;
  • utilize distributed computation infrastructures to efficiently apply machine learning algorithms;
  • properly evaluate a machine learning algorithm's performance in a real-life context.
Machine learning addresses the fundamental problem of developing computer algorithms that can harness the vast amounts of digital data available in the 21st century and then use this data in an intelligent way to solve a variety of real-world problems. Examples of such problems are recommender systems, (neuro) image analysis, intrusion detection, spam filtering, automated reasoning, systems biology, medical diagnosis, speech analysis, and many more. The goal of this course is to learn how to tackle specific real-life problems through the selection and application of state-of-the-art machine learning algorithms, notably by entering international machine learning competitions organized at Kaggle. In particular, this course intends to teach students who are already familiar with the (theoretical) basics of machine learning and deep learning, how state-of-the-art methods are applied in a realistic practical problem setting.

Instructional Modes
  • Introduction lectures for each of the two competitions tackled during the course
  • Response course
  • Presentation
  • Self-study
To follow this course, students need to be familiar with the basics of machine learning and deep learning, additionally, experience with programming is also needed.
This course is not an introduction to machine learning.
Presumed foreknowledge
A master course on machine learning: NWI-IMC056 or SOW-MKI75;
and a master course on deep-learning: NWI-IMC070 or SOW-BKI230
Test information
Group work, flash talk presentations, and final reports, one for each competition. Individual performance will also be assessed through peer review.
Examples of running machine learning competitions can be found at https://www.kaggle.com
During the course two competitions will be tackled, generally, the first competition is one we organize ourselves  using data related to ongoing research at the Radboud University, and the second is a Kaggle challenge.

This course is designed for master students in Computing Science and Artificial Intelligence, who have already completed courses in machine learning and deep-learning. This course is not an introduction to machine learning; students in Physics, Neurophysics and Mathematics who are interested in this topic are advised to first follow the courses listed in the presumed foreknowledge section.
Assumed previous knowledge
Data mining,
A bachelor or master course on Neural Networks

Previous knowledge can be gained by
NWI-IBI008 Data Mining;
NWI-IMC070 Deep Learning or SOW-BKI230A Deep Learning.

Required materials
Scientific papers and material provided by the teachers during the introductory lectures and during the teams-teacher meetings. Also, material available at Kaggle related to the competition(s.)

Instructional modes
Course occurrence

Attendance MandatoryYes

Final grade
Test weight1
OpportunitiesBlock KW4, Block KW4

See detailed description under Test Information