MATE5427 Foundations of Machine Learning I (5 cr)
Cooperation network course
Network: Cross-institutional studies in advanced courses in mathematics and statistics
This course is offered through the Network for Advanced Studies in Mathematics. These studies are available for the following degree students:
- Bachelor's Degree Programme in Mathematics
- Master's Degree Programme in Mathematics
- Bachelor's Degree Programme in Mathematics (Subject Teacher)
- Master's Degree Programme in Mathematics (Subject Teacher)
- Bachelor's Degree Programme in Mathematics, Chemistry or Physics Subject Teacher Education and Primary Teacher Education (Specialication in Mathematics)
- Master's Degree Programme in Mathematics, Chemistry or Physics Subject Teacher Education and Primary Teacher Education (Specialication in Mathematics)
- Doctoral Programme in Mathematics and Statistics
- Doctoral Programme in Mathematics and Science (Specialication in Mathematics)
Grading scale:
0-5
Description
This course (in 3 parts) is a general introduction to machine learning focusing on the fundamental modern topics in this field and providing the theoretical bases and concepts behind key algorithms. The course aims to provide a deep understanding of the nature of the problems addressed in machine learning and of the computational strategies behind the most popular approaches in this field. The topics we cover include design and analysis of machine learning experiments, supervised learning, unsupervised learning, active learning, reinforcement learning, Bayesian decision theory, parametric methods, multivariate methods, multilayer perceptrons, local models, hidden Markov models, kernel machines, graphical models. Short programming assignments include hands-on experiments with various learning algorithms.
Learning outcomes
By the end of this course students will be able to formulate the typical machine learning problems as optimisation problems and will understand the mathematical foundations of the key solutions in the practice of machine learning.
Additional information
Lectures are not given every year but it's also possible to take the course independently. Academic year 2026-2026 available only for independent study.
Description of prerequisites
Maturity in computer programming, probability, calculus, and linear algebra.