In 2023, I read 87 papers and 26 non-technical books. 87 papers is slightly more than my previous record (82 papers in 2022), and I’ve never even been remotely close to reading 26 books in a year. Deciding to read more books is definitely…
I am a postdoctoral researcher in the group of Mattias Rantalainen at Karolinska Institutet in Stockholm, working on machine learning and computer vision for computational pathology. My research focuses on how to build and evaluate reliable machine learning models for safe data-driven medicine. It has often included regression problems, uncertainty estimation methods or energy-based models.
I received my BSc in Applied Physics and Electrical Engineering in 2016 and my MSc in Electrical Engineering in 2018, both from Linköping University. During my MSc, I also spent one year as a graduate exchange student at Stanford University. I received my PhD in Machine Learning in 2023 from Uppsala University for the thesis Towards Accurate and Reliable Deep Regression Models. During my PhD, I was supervised by Thomas Schön and Martin Danelljan.
[Jan 29, 2024] New blog post: My Year of Reading in 2023.
[Jan 16, 2024] Accepted paper: Controlling Vision-Language Models for Multi-Task Image Restoration, work lead by the incredibly skilled Ziwei Luo, has been accepted to ICLR 2024.
[Dec 8, 2023] I have joined the group of Mattias Rantalainen at Karolinska Institutet as a postdoc to work on computational pathology.
[Nov 30, 2023] I have successfully defended my PhD thesis Towards Accurate and Reliable Deep Regression Models [pdf] [DiVA] [slides] [video].
[Oct 31, 2023] Invited talk: I presented How Reliable is Your Regression Model’s Uncertainty Under Real-World Distribution Shifts? [slides] at the DFKI Augmented Vision Workshop.
[Oct 2, 2023] New preprint: Controlling Vision-Language Models for Multi-Task Image Restoration [arXiv] [code] [project].
[Jun 28, 2023] Accepted paper: How Reliable is Your Regression Model’s Uncertainty Under Real-World Distribution Shifts? has been accepted to TMLR.
[Jun 22, 2023] New blog post: The How and Why of Reading 300 Papers in 5 Years.
Click here for older news.
1RT495 | Automatic Control II | MSc
Teaching Assistant (Swedish: Lektionsledare)
Spring II 2023
1RT700 | Statistical Machine Learning | MSc
Teaching Assistant
Autumn II 2022
1RT890 | Empirical Modelling | MSc
Teaching Assistant (Swedish: Lektionsledare)
Autumn I 2022
1RT700 | Statistical Machine Learning | MSc
Teaching Assistant
Spring I 2022
1RT890 | Empirical Modelling | MSc
Teaching Assistant (Swedish: Lektionsledare)
Autumn I 2021
1RT495 | Automatic Control II | MSc
Teaching Assistant
Spring II 2021
1RT490 | Automatic Control I | BSc
Teaching Assistant (Swedish: Lektionsledare)
Spring I 2021
1RT890 | Empirical Modelling | MSc
Teaching Assistant (Swedish: Lektionsledare)
Autumn I 2020
1RT700 | Statistical Machine Learning | MSc
Lab Assistant
Spring I 2020
1RT490 | Automatic Control I | BSc
Teaching Assistant (Swedish: Lektionsledare)
Spring I 2020
1RT490 | Automatic Control I | BSc
Teaching Assistant (Swedish: Lektionsledare)
Autumn I 2019
Deep Learning | PhD (Broad)
Teaching Assistant
Spring II 2019
1RT700 | Statistical Machine Learning | MSc
Lab Assistant
Spring I 2019
1RT490 | Automatic Control I | BSc
Teaching Assistant (Swedish: Lektionsledare)
Spring I 2019
TATA24 | Linear Algebra | BSc
Teaching Assistant (Swedish: Mentor)
Autumn 2015
TATM79 | Foundation Course in Mathematics | BSc
Teaching Assistant (Swedish: Handledare)
Autumn 2015
TATA24 | Linear Algebra | BSc
Teaching Assistant (Swedish: Mentor)
Autumn 2014
TAIU10 | Calculus, one variable - Preparatory course | BSc
Teaching Assistant (Swedish: Lektionsledare)
Autumn 2014
80 papers in total.
How Reliable is Your Regression Model’s Uncertainty Under Real-World Distribution Shifts?
RISE Learning Machines Seminars | Online | [slides]
March 21, 2024
How Reliable is Your Regression Model’s Uncertainty Under Real-World Distribution Shifts?
DFKI Augmented Vision Workshop | Online | [slides]
October 31, 2023
Accurate 3D Object Detection using Energy-Based Models
Zenseact | Online | [slides]
January 29, 2021
Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision
Zenuity | Gothenburg, Sweden | [slides]
June 18, 2019
Towards Accurate and Reliable Deep Regression Models
PhD defense | Uppsala, Sweden | [slides] [video]
November 30, 2023
Some Advice for New (and Old?) PhD Students
SysCon μ seminar at our weekly division meeting | Uppsala, Sweden | [slides]
March 16, 2023
Can You Trust Your Regression Model’s Uncertainty Under Distribution Shifts?
SysCon μ seminar at our weekly division meeting | Uppsala, Sweden | [slides]
September 15, 2022
Energy-Based Probabilistic Regression in Computer Vision
Half-time seminar | Online | [slides]
February 3, 2022
Regression using Energy-Based Models and Noise Contrastive Estimation
SysCon μ seminar at our weekly division meeting | Online | [slides]
February 12, 2021
Semi-Flipped Classroom with Scalable-Learning and CATs
Pedagogical course project presentation | Uppsala, Sweden | [slides]
December 18, 2019
Deep Conditional Target Densities for Accurate Regression
SysCon μ seminar at our weekly division meeting | Uppsala, Sweden | [slides]
November 1, 2019
Predictive Uncertainty Estimation with Neural Networks
SysCon μ seminar at our weekly division meeting | Uppsala, Sweden | [slides]
March 22, 2019
I categorize, annotate and write comments for all research papers I read, and share this publicly on GitHub (380+ papers since September 2018). Feel free to reach out with any questions or suggested reading. In June 2023, I also wrote the blog post The How and Why of Reading 300 Papers in 5 Years about this.
From 2018 to 2023, I organized the SysCon machine learning reading group.
I have also started to really enjoy reading non-technical books, e.g. about ethics and political philosophy. Since late 2022, I have read the following books:
30 books in total.
In 2023, I read 87 papers and 26 non-technical books. 87 papers is slightly more than my previous record (82 papers in 2022), and I’ve never even been remotely close to reading 26 books in a year. Deciding to read more books is definitely…
Since I started my PhD almost five years ago, I have categorized, annotated and written short comments for all research papers I read in detail. I share this publicly in a GitHub repository, and recently reached 300 read papers. To mark this milestone, I decided to share some thoughts on why I think it’s important to read a lot of papers, and how I organize my reading. I also compiled some paper statistics, along with a list of 30 papers that I found particularly interesting…
We have created a video in which we try to explain how machine learning works and how it can be used to help doctors. The explanation is tailored to grade 7-9 students, and the idea is that you only should need to know about basic linear functions (straight lines) to understand everything.
When I first got interested in deep learning a couple of years ago, I started out using TensorFlow. In early 2018 I then decided to switch to PyTorch, a decision that I’ve been very happy with ever since…
During the years of my PhD, running turned into an important part of my life, crucial in order to keep me productive and in a good mental state throughout the work days and weeks. I’m a relatively serious runner, but I run mostly just because it’s a lot of fun and a great way to explore your surroundings, and because it’s good for both my physical and mental health. My training can be followed on Strava.
From Sep 10 2020 until Dec 31 2023, I was on a run streak (running at least 2 km outside every day) of 1208 days. I started a new modified run/walk streak on Jan 2 2024 (just walking 1 km outside is fine on proper sick days).
81.5 credits in total.
29 units (58 credits) in total.
277 credits in total.