TMA4268 Statistical Learning, spring 2026

News Box:

The first exercise class will be on Monday the 19th of January, in A4-112. We will do some live coding in the first 45 minutes, focusing on Problem 5 in Module 2 exercise.
In the exercise class on Monday the 2nd of February we will be going through parts of Problem 6 on the Module 4 exercise.
Compulsory exercise #1 is now out. See the "Compulsory exercise 1"-tab for details.
The code from the first four exercise classes is now on Blackboard under Learning Materials
In the exercise class on Monday the 23rd of February we will do some exploration of the ISLR2::Credit dataset based on Problems 4 (forward selection), 5 (ridge regression), and 6 (lasso regression) on the Module 6 exercise sheet.
The room for the exercise class has been changed to KJL22.
In the next exercise class (02.03) we will be looking a Problem 3 and 4 in the Module 7 exercise.
In the next exercise class (09.03) we will be looking a Problem 2 in the Module 8 exercise.
In the next exercise class (16.03) we will try to predict spam-emails using boosting.
~~I (Simen) am currently in KJL22 if you need guidance with the project. I will be here until 12:00.~~
In the next exercise class (12.04) we will look at Problem 1 and 3 from the Module 10 exercise.
I will not have time to prepare anything for the next exercise class (19.04), so it will be a normal exercise class. Please come by if you have questions about the course material, the exercise problems, or previous exam problems.
I have sadly not had any time to prepare anything this week either, so the exercise class (26.04) is also a normal exercise class. I apalogise that I will not be able to show you an example of neural networks. Still, please come by if you have questions about the course material, the exercise problems, or previous exam problems.

Course times/place: Monday 08:15-10:00, S6 - Tuesday 12:15-14:00, KJL5

Exercise sessions/place: Monday 10:15-12:00, KJL22

Lecturer: Benjamin Dunn

Teaching Assistants: Simen Knutsen Furset

Course material: All the course and learning material will be presented on this course page.

In addition we will use Blackboard for handing in compulsory exercises (two in total).

Recommended previous knowledge:

The course is based on TMA4240/4245 Statistics, or equivalent.
Good knowledge of matrix algebra and understanding of optimization.
Good understanding of programming - strong emphasis on R programming (you will learn R in this course).

These are the targeted learning outcomes

1. Knowledge. The student has knowledge about the most popular statistical models and methods that are used for prediction in science and technology, with emphasis on regression- og classification-type statistical models.

2. Skills. The student can, based on an existing data set, choose a suitable statistical model, apply sound statistical methods, and perform the analyses using statistical software. The student can present, interpret and communicate the results from the statistical analyses, and knows which conclusions can be drawn from the analyses, and what are the caveats.