Biography
I am a PhD student at KTH Royal Institute of Technology, Stockholm. Currently, I work on artificial intelligence, machine learning, and computer vision. I am supervised by Ragnar Thobaben and Mikael Skoglund. I received both my MSc and BSc in electrical engineering from KTH, and spent a year as an exchange student at Imperial College London, where I wrote my MSc thesis at the Information Processing and Communications Lab under Deniz Gündüz.
I work on understanding machine learning systems. I use my background in information theory and error-correcting codes to design and analyse deep learning systems. The goal of my research is to develop more efficient learning algorithms which better capture features of the data, and whose performance generalise to unseen settings.
Feel free to reach out to me if you find these topics interesting!
Papers
Latest Paper Title
Martin Lindström, Coauthor 1, Coauthor 2
GRaM 2024
This is a nice abstract. \(x^2\)
| arXiv | BibTeX |
First paper titles
Martin Lindström, Coauthor 1, Coauthor 2
GRaM 2024
This is a nice abstract.
| arXiv | BibTeX |
Teaching Experience
Miscellaneous
- BETA Mathematics Handbook by Råde and Westergren — a 500 page formula sheet which contains almost everything from linear algebra, geometry, and calculus
- Elements of Information Theory by Cover & Thomas — maybe the most user-friendly introduction to information theory
- Information Theory: From Coding to Learning by Polyanskiy & Wu — a more advanced treatment of information theory, which contains almost all you need to know about the topic
- Convex Optimization by Boyd & Vandenberghe — motivation superfluous
- Understanding Machine Learning: From Theory to Algorithms by Shalev-Shwartz and Ben-David — a good introduction to classical theoretical machine learning, such as PAC-learnability, SVMs, and much more
- A Course in Real Analysis by McDonald and Weiss — I have found that a basic understanding of measure-theoretic probability is useful to know. Unfortunately, it is a dense subject to tackle. This is the most accessible book I have found.