The topic for the lab is unsupervised learning using PCA and variational autoencoders.
The lab is scheduled for 4 hours, and done in groups of 2 students each. There are three different sessions scheduled, each group should attend one of these. The lab is mandatory and examination will be done during these 4 hours, no report needs to be written. This year, the supervision and grading of the lab will be done via zoom. If you prefer, you can do the lab before the lab session and only attend the session to be graded. However, the preparatory exercises must always be done before the lab session.
Lab instructions: lab_instructions.pdf
Additional material: introduction.ipynb lab_code.zip
Queue list: https://docs.google.com/document/d/1EPoaDW1bR0lwD5aYazpnFpuzRlxiGRg3MFc1WbuFx1Y/edit?usp=sharing
You can either choose to do the lab in your web browser via Google colab or locally on your computer. If you choose the last option, make sure to have all software (notably PyTorch) installed before the lab session, see the instructions for details.
Read and do the preparatory exercises before the lab session.
1 . Choose a partner that you want to do the lab with.
2. Both you and your partner register to one of the lab sessions in the course calendar. Find the sessions via the "Find appointment" button. Write in the comment field with whom you do the lab.
If you don't find a partner, you can sign up to a lab sessions alone and we will group you as the lab starts.
If you have any questions regarding the lab, primarily use Discussion forum - Laboratory work for your questions.
If you find it more appropriate, you can also email David Widmann (for questions regarding lab instructions) or Niklas Wahlström (for questions regarding lab registration).