Applied Machine Learning - Week 4

Monday the 11th - Friday the 15th of May 2026

Click here to register your final project group (don't worry - not final).

See Andrej Kaparthy's description of how to reproduce GPT2 from scratch (long but fantastic).


Monday 11th of May (afternoon):
Lectures: We will be discussing (Variational) Auto-Encoders, anomaly detection, and GANs.

Exercise: The exercise is about classifying digits i.e. the MNIST data, but this time in an unsupervised manner with an autoencoder.
     Following this we will repeat the exercise, this time with a Variational AutoEncoder. These techniques are also useful for anomaly detection in images.


Wednesday 13th of May (morning):
Lectures: GPU accelerated data analysis (Mads Kristensen, Nvidia - formerly NBI).

Exercise: Following the lecture of Mads, you should try to implement some of the (many) methods for speeding up your code.
     Another important aspect is the speed of the Data Loader, for which we provide an example.
     Alternatively (or in addition), work on (preparing) final project.


Wednesday 13th of May (afternoon):
Lectures: Final projects kickoff. Introducing Potential Datasets and Projects (TP).

Exercise: The exercise simply to get set up for the final project. It is highly advantages to get hold of your data (or part of it) before this.
     During these exercises you should aim to settle your final project groups and discuss what data to work on.
     Things to consider are data, group, goals of analysis, and methods. We will sit down with you and talk about this.

---

Last updated: 6th of May 2026 by Troels Petersen.