Machine Learning

Education facts

Code: ETE391

<p>This course is aimed at those who want to gain a broad knowledge of different types of machine learning and an understanding of how different machine learning methods work, either if you are working as an engineer and want further education or want to complement on-going higher education with a course in machine learning. The course takes off with an introduction to the field of machine learning, discussing the three different basic principles for machine learning – Supervised, Unsupervised, and Reinforcement Learning. Then we take a closer look at some specific methods within each of these areas. Within Supervised Learning, we first look at linear classifiers followed by Neural Networks, including Deep Learning and Convolutional Neural Networks. Within the category Unsupervised Learning, we cover data analysis methods such as Principal Component Analysis and Clustering. Finally, we look at Q-learning as an example of Reinforcement Learning.&nbsp;</p><p>The course contains 4 programming exercises that should be reported in written form and comprise the examination of the course. The course is given completely on distance with scheduled occasions for seminars and supervision.&nbsp;</p><p>As the course is given in English, this is a prerequisite. If your high school qualifications are not already on your pages on antagning.se, you need to upload your high school diploma, or equivalent, on antagning.se in connection with your application.</p>

Entry requirements

90 ECTS credtis passed in an engeineering subject and/or natural sciences of which at least 5 ECTS credits Multivariate calculus, 5 ECTS credits Linear Algebra, 5 ECTS credits Statistics, 5 ECTS credits Python programming or equivalent work experience of at least 1 year on a half time basis where Python programming is part of the work tasks English corresponding to the level of English in Swedish upper secondary education (Engelska 6 or Engelska nivå 2) Exemption from Swedish

Education offerings

Each offering has its own dates and conditions. Closed offerings are retained as history and do not mean that a new application is open.

• Machine Learning

  Linköping University

  Start date: 31 August 2026

  End date: 1 November 2026

  Pace of study: 33 %