Advanced Probabilistic Machine Learning - Lab

Topic

The topic for the lab is unsupervised learning using PCA and variational autoencoders.

Helpdesk session

As described below, it is mandatory to do the preparatory exercises in advance to your lab session. (Otherwise, you won't be able to finish on time.) On October 15, 08.15-10.00 in room ITC 2214 there will be a helpdesk session for the preparatory exercises. You are welcome to pass by and discuss and ask questions about the preparatory exercises.

Registration

The registration for the lab is done in the student portal. If you have any questions, please contact Niklas Wahlström.

Format

The lab is scheduled for 4 hours, and done in groups of 2 students each. There are two different sessions scheduled (see TimeEdit for exact dates), each group should attend one of these. The lab is mandatory and examination will be done on site, no report needs to be written.

Instructions

The lab instructions: VAE_lab_instructions.pdf
The code and data files related to the lab: introduction.ipynb lab_code.zip

You can choose to use either the computers in the computer room, or your private laptop. If you use your private laptop, 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.

We recommend you to bring a printed version of the lab instruction to the lab session. Printed lab instructions will be handed out on the lecture on Monday October 7 and Thursday October 10. You can also get a printed copy from the office of David Widmann (ITC:2303) or Niklas Wahlström (ITC:2319).