Statistical Machine Learning - Lab
Topic
The topic for the lab is deep learning. The goal of the lab is
- to learn how to build and train a neural network,
- to learn how to improve the neural network model and its training, and
- to get a glimpse of a state-of-the-art software library (PyTorch) for deep learning.
We will look at two applications with image classification, namely
- classification of hand-written digits by training and using a neural network, and
- classification of real world images using a pre-trained deep neural network.
Registration
The registration for the lab is done in the student portal. If you have any questions, please contact Johan Wågberg.
Format
The lab is scheduled for 4 hours, and done in groups of 2 students each. There are four 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 instruction will be published in due time prior the lab.
The lab instructions: DLlab_instructions_python.pdf
The code related to the lab: introduction.ipynb DLlab_code_python.zip.
The data will be downloaded automatically the first time you run the code.
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 section 2 and do the preparatory exercises in Section 3 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 deep learning lectures Monday February 24 and Thursday February 27. You can also get a printed copy from the office of Niklas Wahlström (ITC:2319) or David Widmann (ITC:2303).