At the UiT Machine Learning Group we teach several courses on, and related to, machine learning. The courses are an important part of our study programs, and most require some background in mathematics, physics and programming.

The university campus in Tromsø.

Photo: Screen media


The Machine Learning Group has been assigned ownership (or co-ownership) of the following courses at the Department of Physics and Technology, for which we are responsible for teaching and course development:

Members of the Machine Learning Group are also teaching the following courses:


FYS-2010 Image Processing

The course introduces fundamental topics in digital image analysis, comprising both mathematical operations on images (image processing) and their use in image understanding and interpretation (computer vision). The course covers mathematical characterization of discrete images, sampling, reconstruction and important image transforms. It teaches image filtering in the spatial and frequency domain covering image enhancements, noise removal, and detection of edge, point and corner features that can be used in vision tasks. It also covers algorithms for object detection and extraction, including thresholding, segmentation and classification. The course describes the evolution from image filtering by convolution with static operators to adaptive processing with convolutional neural networks (CNNs) that learn their filters from data. It gives an introduction to deep learning and training of CNNs for image analysis tasks. The course emphasizes practical exercises. It is relevant for further studies in various fields, such as machine learning, remote sensing (earth observation, space physics, optics, microwaves and ultrasound), automation, robotics, and energy data analytics.

More information on Image Processing can be found on the official course website.

FYS-2021 Machine Learning

The course will introduce the students to the fundamental concepts in machine learning and will study widely used and popular machine learning algorithms for analysing data in the modern society. The course will cover elementary methods for both supervised and unsupervised learning, both for regression and classification. Supervised methods will include technologies such as decision trees, linear discrimination and neural networks. TUnsupervised methods covered will include machine learning methods based on linear algebra as well as standard clustering methods. The course will have a significant practical component, in which various applications will be treated in the form of case studies.

More information on Machine Learning can be found on the official course website.

FYS-3012/8012 Pattern Recognition

The course covers data analysis techniques such as Bayes classifiers, estimation of probability density functions and related non-parametric classification approaches. Further, linear classifiers using least squares are addressed, in addition to simple processing units (neurons) and their extension to artificial neural networks. Linear and non-linear (using kernel functions) support vector machine classifiers are discussed, in addition to feature extraction and data transformation using eigenvector-based methods such as Fisher discriminants. Methods for grouping, or clustering, data are treated in detail, including hierarchical clustering and k-means. Exercises and problem solving, in addition to practical pattern recognition for data analysis using programming, are strongly emphasized. Basic programming skills are required.

More information on Pattern Recognition can be found on the official course website.

Pattern Recognition is also available at PhD level. Please see the official website.

FYS-3033/8033 Deep Learning

Deep Learning, a subfield of machine learning, has in recent years achieved state-of-the-art performance for tasks such as image classification, object detection and natural language processing. This course will study recent deep learning methodology such as e.g. convolutional neural networks, autoencoders and recurrent neural networks, will discuss recent advances in the field, and will provide the students with the required background to implement, train and debug these models. There will be a significant practical component, where students will gain hands-on experience. The course will in addition to deep learning algorithms contain elements of image processing, pattern recognition and statistics.

More information on Deep Learning can be found on the official course website.

Deep Learning is also available at PhD level. Please see the official website.

FYS-3032/8032 Health Data Analysis

This is a new course that will be available from the fall of 2021. More information on this later.

Health Data Analysis will also be available at PhD level.

Special curriculums

Special curriculums can be arranged for individual students and PhD candidates. Previously the following special curriculums has been arranged.

  • Graph Neural Networks

  • Deep Domain Adaptation

  • Natural Language Processing with Deep Learning

  • Bayesian Deep Learning

  • Gaussian Processes

  • Bayesian Modelling

  • Reinforcement Learning

  • Random Forests