The goal of this course is to give an overview of mathematical structures that appear in modern deep neural networks and how these can be used to understand neural networks theoretically. The course is aimed at students familiar with advanced mathematics but not machine learning.
At the end of the course, the students should be able to understand current research literature in the field and carry out their own projects in deep learning.
The course starts with a concise introduction to deep learning, followed by deeper dives into the topics of equivariant neural networks, large width neural networks and geometrical aspects of explainable AI. Additional lectures cover the practical aspects of implementing neural network training on Google Cloud infrastructure. The lectures are accompanied by exercise sessions and homework assignments, where students gain hands-on experience with training neural networks. The course is graded with a project.
Next course instance: LP3 of the academic year 2025/2026
This course is part of the Software Engineering and Management bachelor’s programme at Gothenburg University. The course is taken by students in the first year of the program and introduces basic mathematical concepts and reasoning and discusses important techniques and results required in later courses. The content of the course includes
Next course instance: LP1 of the academic year 2025/2026