Schedule and course plan

Period 2 Where and when Activity Reading Examination Tue 3 Nov

10:15-12:00

M1

Lecture 1: Introduction

Hedvig Kjellström

Bishop 1

Bishop 2, use as a math reference all through the course

Wed 4 Nov

10.15-12.00

M1

Lecture 2: Regression

Python Code

Carl Henrik Ek

Bishop 6.4 Thu 5 Nov

13.15-15.00

M2

Lecture 3: Gaussian Processes

Python Code

Carl Henrik Ek

Bishop 6.4 Fri 6 Nov

15.15-17.00

V1

Exercise 1: Derivations

Carl Henrik Ek

Wed 11 Nov

10.15-12.00

V3

Lecture 4: Representation Learning

Carl Henrik Ek

Bishop 12.2, 12.4 Thu 12 Nov

13.15-15.00

L1

Lecture 5: Approximative Inference

Carl Henrik Ek

Bishop 6.4.6, 10.1, 10.2

Bishop 10.3, optional

Fri 13 Nov

15.15-19.00

V1

Exercise 2-3: Variational Bayes

Carl Henrik Ek

Tue 17 Nov

10.15-12.00

D3

Lecture 6: Graphical Models

Jens Lagergren

Bishop 8.1-8.3 Wed 18 Nov

10.15-12.00

V22 (small room)

Lecture 7: Graphical Models contd, Hidden Markov Models

Jens Lagergren

Bishop 13.1, 13.2.1, 13.2.2, 13.2.5, 13.2.6 Thu 19 Nov

Hand-in 12.00 NOON

Results on Monday 23 Nov

Reading, slides from Lectures 2-5 Assignment 1 Tue 24 Nov

10.15-12.00

B1

Lecture 8: Expectation-Maximization Applied to Hidden Markov Models

Slides & notes.

Jens Lagergren

Bishop 9.1-9.3 Wed 25 Nov

10.15-12.00

E3

Lecture 9: Expectation-Maximization contd

Jens Lagergren

Slides & notes.

Thu 26 Nov

13.15-15.00

B3

Exercise 4: Lectures 6-9

Jens Lagergren

Training HMMs in more detail

Fri 27 Nov

15.15-17.00

E3

Lecture 10: Non-Gaussian and Discrete Latent Variable Models

Hedvig Kjellström

Bishop 8.2.2, 12.4.1

Hyvärinen and Oja

Tue 1 Dec

10.15-12.00

M2

Lecture 11: Bag of Words, Topic Models

Hedvig Kjellström

Blei and Lafferty

Wed 2 Dec

10.15-12.00

K2

Exercise 5: Probabilistic Independent Component Analysis

Whiteboard photos: 1 2 3 4 5 6 7

Hedvig Kjellström

Beckmann and Smith, optional Thu 3 Dec

13.15-15.00

L51 (small room)

Lecture 12: Sampling

Hedvig Kjellström

Whiteboard photo: 1

Bishop 11.1-11.3

Griffiths

Fri 4 Dec

15.15-17.00

E3

Lecture 13: The Structure of a Scientific Paper

Hedvig Kjellström

Allen

Duvenaud et al.

Tue 8 Dec

12.00-13.00

Room 1448, Lindstedtsv 3 floor 4

Help session about Assignment 2, Task 2.1-2.4

Jens Lagergren

Tue 15 Dec

10.15-12.00

K2

Exercise 6: State-of-the-Art in Machine Learning

Hedvig Kjellström

Wed 16 Dec Hand-in 12.00 NOON

Results on Wednesday 23 Dec

Reading, slides from Lectures 6-12 Assignment 2 Mon 18 Jan

14.00-18.00

E52 (small room)

Hand-in 12.00 NOON

Oral project presentations, 10 min per project group, SCHEDULE TBD¶ .¶

Presence is only needed in the 2h session when your group presents. You are allowed to attend the other session if there is space left in the room.¶

Give slides to Hedvig on a stick before the start of the session. Very strict time deadlines!¶

Session 1 ¶

14.10 Group 16¶

14.20 Group 14¶

14.30 Group 12¶

14.40 Group 10¶

14.50 Group 8¶

15.00 Group 6¶

15.10 Group 4¶

15.20 Group 2¶

15.30 Henrik Talborn¶

15.40 Yavor Kovachev¶

15.50 Ramón Heberto Martinez Mayorquin¶

Session 2¶

16.10 Group 17¶

16.20 Group 15¶

16.30 Group 13¶

16.40 Group 11¶

16.50 Group 9¶

17.00 Group 7¶

17.10 Group 5¶

17.20 Group 3¶

17.30 Group 1¶

17.40 Hanwei Wu

Paper, slides from Lecture 13 Project