Course Syllabus

Jump to Today

Welcome to the course pages for EDAP30 / EDA090F - Advanced Applied Machine Learning

Links to the official course plan in Swedish and English.

Please note that information on this page may change slightly, particularly regarding exact dates. Anything that looks weird might be due to a miss when transferring information from last year's course occasion - please ask in such a case!

General information

The course will start on Monday, March 23rd, and all places will be filled according to the rules regarding prerequisites and ranking as explained below.

The course aims to give insight into more advanced machine learning topics. Mainly, we will cover Kernel methods and Bayesian Optimization, Deep learning for sequential data, Generative ML, and Reinforcement learning.

Registration and admission information

2026-03-03: To keep your seat in the course (if notified that you have one), you need to 

  • Attend the first lecture on March 24th, or notify Davide Tateo (davide.tateo@cs.lth.se) that you cannot make it. Note that you should have a valid reason for not attending, like illness, a work schedule you could not modify, or study-related travels.
  • Sign up for and attend the first lab session on Thursday, March 27st or Friday 28th.
  • Join the Discord channel: https://discord.gg/MTvQEY6ksk

 

Registration information for Ph.D. students (EDAN95F):

2026-03-03: Contact Davide Tateo by e-mail (davide.tateo@cs.lth.se), and we will let you know what the situation is.

 

Communication during the course:

As for EDAN96, we will use Discord as a means of communication and to organize help/presentation sign-up in lab sessions. You find the Discord link on the page Assignments and lab sessions, general info (Page with lab session info)

Syllabus

Sessions and Assignments: The course consists of 14 lectures, 7 lab sessions (some are compulsory), 4 programming assignments (labs) that should be completed in pairs, and 3 individual homework assignments (reports), corresponding to three of the programming assignments. To keep your seat in the course, you need to attend the first lab session (technical setup support). See Assignments and lab sessions, general info (page with info on lab sessions) to learn more about the lab sessions.

Lectures will be held by four teachers:

  • Davide Tateo (DT),  course responsible
  • Erik Hellsten (EH)
  • Son Vu (SV)
  • Marcus Klang (MK)

Modules: The course has 5 Canvas modules (0-4), grouping related lectures and assignments.
Module 0 (DT) gathers the first and last lectures and gives general information about the course.
Modules 1-4 contain 2-4 lectures each, and have the course content distribution of the following topics and methods to be discussed:

  • Module 1 (EH): Kernel Methods, Gaussian processes, Bayesian optimization, Hyperparameter optimization, etc.
  • Module 2 (SV): RNNs, Transformers, etc.
  • Module 3 (MK): Image classification, generative AI, etc.
  • Module 4 (DT): Action learning and Markov decision processes, RL, etc.

Teaching assistants: will take care of the lab sessions and support you in general with the course material.

For this edition of the course, the TAs will be:

  • Hashim Ismail (PhD student)
  • Jialong Li (PhD student)
  • Jonathan Cederlund
  • Olle Persson

Contact information and office hours for teachers and TAs can be found on the Contacts page (Contacts).

Examination: Fulfilling all assignments (programming assignments in pairs, homework assignments individually) will give the full course credits (7.5 ECTS) and a passing grade "3", as well as allow you to take the optional exam, with which it is then possible to get a higher grade ("4", or "5").

If you are a Ph.D. student registered for EDA090F, fulfilling all assignments (programming assignments in small groups, including discussing them in a seminar session (upon agreement), homework assignments individually) will give you the full course credits (7.5 ECTS) and a passing grade (G for "godkänd / passed") on the U/G scale. 


Overview of the course events per course/calendar week (will be updated continuously):

week / cw Lectures (topics)

Assignment announced

 Programming assignments (Labs) due Reports due
1 / 13

23/03: Lecture 1  - Module 0 - Introduction to the course (DT 1)

25/03: Lecture 2 - Module 1 - Introduction and probability theory (EH 1)

23/03: Assignment 0: Tech setup


25/03: Assignment 1 [BO] (Lab & report)

 27/03: Tech setup (OBS, compulsory)
2 / 14 30/03:  Lecture 3 -  Module 1 - Kernel methods (EH 2)
01/04:  Lecture 4 -  Module 1 - Gaussian Processes and Bayesian optimization (EH 3)

 
  Spring Break

 
3 / 17

20/04:  Lecture 5 - Module 2 - Neural networks and NLP (SV 1)


22/04:  Lecture 6 - Module 2 - Generative Language Models and RAGs (SV 2)

23/04: Assignment 2 [RNNs & Transformers] (Lab & report)

 24/04: Programming Assignment 1 [BO]
4 / 18

27/04:  Lecture 7 - Module 3 -  Common Tasks, Architectures and Transfer Learning for Image Data - (MK 1)

29/04: Lecture 8 -  Module 3 - Generative Image Models: VAE and GAN (MK 2)

 

   01/05: Report for Assignment 1 [BO]
5 / 19

04/05:   Lecture 9 - Module 3 - Generative Image Models: Diffusion and Normalizing Flows (MK 3)

06/05:  Lecture 10 - Module 1 - Further topics (EH 4)

04/05: Assignment 3 [GenAI] (Lab & report)

 08/05: Programming Assignment 2 [GPT-2]
6 / 20

11/05:  Lecture 11 -  Module 4 - Introduction to Reinforcement Learning (DT 2)

13/05:  Lecture 12 -  Module 4 - Temporal Difference Learning (DT 3)

 13/05: Assignment 4 [RL] (Only Lab) 15/05: Report Assignment 2 [GPT-2]
7 / 21

18/05:  Lecture 13 - Module 4 - Function Approximation (DT 4)

20/05:  Lecture 14 -  Module 4 - Policy Gradient and Actor-Critic (DT 5)

 

22/05: Programming Assignment 3 [GenAI] 

22/05: Report for Assignment 3 [GenAI]
8 / 22

25/05:  Lecture 15 -  Module 2 - Agentic Systems and Industrial Applications (SV 3)

27/05:  Lecture 16 -  DT 6 - Wrap-up

 29/05: Programming Assignment 4 [RL]

 

Course Summary:

Course Summary
Date Details Due