Lectures
The course comprises 10 lectures for 1RT705 and additional 4 lectures for 1RT003.
| Lecture | Lecturer | Reading | Slides |
Recordings 2021 |
Recordings 2020 |
|
| F1 | Introduction, probabilistic modeling | NW | [B] 1.1-1.2.3 | L1-2021 | L1 -2020F | |
| F2 | Conjugate prior, Binomial-Beta pair, Multivariate Gaussian | NW | [B] 2.1, 2.3.1-2.3.6, 2.4, [LWLS] 9.A, Gaussian distribution formulas Download Gaussian distribution formulas | pdf Download pdf | L2-2021 | Last part of L1 above and parts of L2 below |
| F3 | Bayesian linear regression, marginal likelihood | NW | [B] 3.3-3.4, [LWLS] 9.1-9.2 | pdf Download pdf | L3-2021 | L2 -2020 |
| F4 | Bayesian graphical models | NW | [B] 8, 8.1, 8.2 | pdf Download pdf notes Download notes poll results Links to an external site. | L6-2021 | L3 -2020 |
| F5 | Monte Carlo methods | JS | [B] 11, 11.1.4, 11.2-11.3 | pdf Download pdf | L7-2021 | L4 -2020 |
| F6 | Factor Graphs and message passing (discrete) | NW | [B] 8.4.3, 8.4-8.4.4 | pdf Download pdf | L5 -2020 | |
| F7 | Message passing (Gaussian) and moment matching | NW | [B] 10.7.2*, (13.3) Gaussian distribution formulas Download Gaussian distribution formulas |
pdf Download pdf |
L9-2021 (2nd part)
|
|
| Guest lecture: Better priors for everyone, Arto Klami, University of Helsinki | Abstract | pdf Download pdf |
|
|||
| F8 | Gaussian processes I (only 1RT003) | ZZ | [LWLS] 9.3, [B] 6.4.1, 6.4.2 | lecture_gp_handout.pdf Download lecture_gp_handout.pdf | L4-2021 | L7 -2020 |
| F9 | Gaussian processes II (only 1RT003) | ZZ | Lecture note and codes Links to an external site. | lecture_gp_handout.pdf Download lecture_gp_handout.pdf | L5-2021 | L8 -2020 |
| F10 | Variational inference (only 1RT003) | JS | [B] 1.6.1, VI tutorial Links to an external site. | pdf Download pdf | L10-2021 | L6 -2020 |
| F11 | Unsupervised learning | TS | [B] 2.5, 12.1, 12.2 (but not 12.2.1-4) |
pdf Download pdf | L11-2021 | L9 -2020 |
| F12 | Semi-supervised learning and generative models | TS | [LWLS] 10.1, 10.3 | pdf Download pdf | L12-2021 | New in 2021 |
| F13 | Variational autoencoder (only part of 1RT003) | DG | [KW] 1-2.4 | pdf Download pdf | L13-2021 | L10 -2020 |
| F14 | Summary | NW | pdf Download pdf |
(you need to be enrolled to the course and logged in to access the recording)
Lectures F8, F9, F10, F13 covers material which is part of the course content of 1RT003 only. Note that in the schedule the lectures are numbered according to the table above, also for 1RT705.
- [B] Christopher M. Bishop, Pattern Recognition and Machine Learning
. - [LWLS] Andreas Lindholm, Niklas Wahlström, Fredrik Lindsten, and Thomas B. Schön Machine Learning - A First Course for Engineers and Scientists Links to an external site.
- [KW] Diederik Kingma and Max Welling, An introduction to Variational Autoencoders Links to an external site.
NW = Niklas Wahlström
JS = Jens Sjölund
ZZ = Zheng Zhao
TS = Thomas Schön
DG = Daniel Gedon
Note that recorded lectures from the previous years cover the material in different order and there might admin info in these which might be obsolete.
* = Bishop explains approximate inference (using Expectation propagation) in graphs in a quite complicated manner. The lecture follows a different approach. The exposition of time series in the lectures is also simpler than Bishop's.