Skip to main content
Department of Information Technology

Deep Learning - Lectures

The course comprises 10 lectures.

# Lecture Lecturer Chapter Slides
1. Introduction, ML basics, linear models NW [GBC] 1, 5, [LWLS] 2.1-2.3, 3.1-3.2.2 Le1
2. Feed forward neural networks NW [GBC] 6.1-6.4, [LWLS] 7.1-7.2, 3.2.3 Le2
3. Optimization: Stochastic gradient and backpropagation TS [GBC] 8.1-8.3,6.5, [LWLS] 7.4 Le3
4. Convolutional neural networks 1 JL [GBC] 9, [LWLS] 7.3 Le4
5. Convolutional neural networks 2 JL [GBC] 9 Le5
6. Over-/underfitting, bias-variance, regularization NW [LWLS] 5, 7.4.4, [GBC] 7 Le6
7. Practical methodology and batch normalization NW [GBC] 8.7.1, 11 Le7
8. Variational inference
9. Variational autoencoders
10. Project proposal presentation

The recommended book for the course is

  • [GBC] Ian Goodfellow, Yoshua Bengio and Aaron Courville Deep Learning, MIT Press, 2016.

We will not follow [GBC] strictly and we do not cover all aspects of the suggested chapters in the lecture. For some lectures in the course, the following lecture notes contain the covered material in a more condensed format.

Another great resource is

which is a bit more hands-on in comparison to [GBC] but does not cover as much and is lacking some details.

For lecture 8 and 9 some additional resources will be used

NW = Niklas Wahlström
TS = Thomas Schön
JL = Joakim Lindblad

Updated  2021-03-04 14:01:29 by Niklas Wahlström.