Course syllabus

Jump to today

Course-PM

TIF360 / FYM360 TIF360 / FYM360 Advanced machine learning with neural networks lp4 VT25 (7.5 hp)

Course is offered by the Department of Physics

Contact details

Examiner

Giovanni Volpe giovanni.volpe@physics.gu.se 

Lecturers

Giovanni Volpe giovanni.volpe@physics.gu.se 
Bernhard Mehlig Bernhard.Mehlig@physics.gu.se
Daniel Midtvedt daniel.midtvedt@physics.gu.se 
Jesus Pineda  jesus.pineda@physics.gu.se  

Lectures and TAs for Laboratories and Projects

Agnese Callegari, agnese.callegari@physics.gu.se 
Daniel Midtvedt daniel.midtvedt@physics.gu.se 
Jesus Pineda  jesus.pineda@physics.gu.se 
Yu-Wei Chang yu-wei.chang@physics.gu.se 
Mirja Granfors mirja.granfors@physics.gu.se
Aarón Domenzain aaron.domenzain@physics.gu.se
Alex Lech alex.lech@physics.gu.se
Fredrik Skärberg fredrik.skarberg@physics.gu.se

 

Course purpose

This course introduces students to recent developments and state-of-the-art methods in machine learning using artificial neural networks. This advanced course builds on Machine learning with neural networks (FFR135) and provides an in-depth analysis of many of the concepts and algorithms that were briefly introduced in that course, with particular emphasis on applications in the natural and engineering sciences. The goal is to become familiar with several advanced machine-learning methods, and to code them efficiently in Python using current neural-network packages. An essential part of the course are projects in deep learning, recurrent learning, and reinforcement learning.

Schedule

TimeEdit, until +2 week from now (graphic)

TimeEdit, complete schedule: (graphic),  (text)

Course literature

DeepLearningCC_placeholder.png

Textbook: Benjamin Midtvedt, Jesús Pineda, Henrik Klein Moberg, Harshith Bachimanchi, Joana B. Pereira, Carlo Manzo, and Giovanni Volpe. Deep Learning Crash Course. No Starch Press, 2025.
https://nostarch.com/deep-learning-crash-course 

GitHub page and jupyter notebooks:  https://github.com/DeepTrackAI/DeepLearningCrashCourse

Suggested reading for background: Bernhard Mehlig, Machine Learning with Neural Networks. Cambridge University Press  (2022)  www.chalmersstore.se or www.adlibris.com

Course design

 

Week Date Time Place Content Chapter To Do
13 25/03 8-10 HC1 Introductory Lecture - B. Mehlig
13 25/03 10-12 HC1 Introductory Lecture - G. Volpe
13 26/03 8-10 HC1 Convolutional Neural Networks for Image Analysis (1) - G. Volpe 3 Revise Notebook 3.1
13 26/03 10-12 SB-D209 Help session - TAs 3
13 26/03  HW1 announced
13 28/03 8-12 SB-H8 Convolutional Neural Networks for Image Analysis (2) - D. Midtvedt 3 Revise Notebooks 3.A and 3.B

 

Week Date Time Place Content Chapter To do
14

31/03 07:00

 Project Registration Opens Register on Canvas
14 1/04 8-12 HB1 Convolutional Neural Networks for Image Analysis (3) - G. Volpe 3 Revise Notebooks 3.C and 3.D
14 1/04 22:00 DEADLINE: Register for HW1 Register on Canvas before the deadline 
14 2/04 8-10 HC2 Encoders-Decoders for Latent Space Manipulation (1) - J. Pineda 4 Revise Notebook 4.1 .
14 2/04 10-12 SB-D209 Help session - TAs
14 2/04
HW2 announced
14 2/04 23:59 DEADLINE: Submit HW1 Submit PDF on Canvas before the deadline
14 3/04 8-12 13-17 SB-D209 HW1 assessment
14 4/04 8-12 HC2 Encoders-Decoders for Latent Space Manipulation (2) - D. Midtvedt 4 Revise Notebooks 4.A and 4.B and 4.C
14 4/04 22:00 DEADLINE: Project Registration Closes Register for Project on Canvas before the deadline

 

Week Date Time Place Content Chapter To do
15 8/04 8-12 HC2 U-Nets for Image Tranformation - J. Pineda 5 Revise Notebooks 5.1, 5.A and 5.B
15 8/04 22:00 DEADLINE: Register for HW2 Register on Canvas before the deadline
15 9/04 8-10 HC1 Self-Supervised Learning to Exploit Symmetries - G. Volpe 6 Revise Notebooks 6.1 and 6.A
15 9/04 10-12 SB-D080 Help session - TAs
14 9/04
HW3 announced  
15 9/04 23:59 DEADLINE: Submit HW2 Submit PDF on Canvas before the deadline
15 10/04 8-12
SB-D080 HW2 assessment
15 10/04  13-17 Sal A HW2 assessment
15 11/04 8-12 HC2 Recurrent Neural Network for Time Series Analysis - D. Midtvedt 7 Revise Notebooks 7.1 and 7.A
15 11/04 16:00 DEADLINE: Communicate project typology (if choosing 2-, 3-people project) No communication must be done if a student chooses to do an individual project.

 

Week Date Time Place Content Chapter To do
17 22/04 12:00 DEADLINE: Submit Project Abstract and Methods Overview Submit to Canvas before the deadline
17 22/04 22:00 DEADLINE: Register for HW3 Register on Canvas before the deadline
17 23/04 8-10 HC1 Attention and Transformation for Sequence Processing - D. Midtvedt 8 Revise Notebooks 8.1 and 8.A
17 23/04 10-12 SB-D080 Q&A Session 1 on Project - TAs
17 23/04
HW4 announced  
17 23/04 23:59 DEADLINE: Submit HW3 Submit PDF on Canvas before the deadline
17 24/04 8-12 13-17
SB-D080 HW3 assessment
17 25/04 8-12 HC2

Generative Adversarial Neural Network for Image Synthesis - D. Midtvedt

 9 Revise Notebooks 9.1 and 9.A

 

Week Date Time Place Content Chapter To do
18 29/04 8-12 HA3 Diffusion Models for Improved Data Generation - D. Midtvedt 10 Revise Notebooks 10.1 and 10.A
18 30/04 8-10 FB Graph Neural Network for Relational Data Analysis - D. Midtvedt 11 Revise Notebook 11.1
18 30/04 10-12 SB-D080 Help session - TAs

 

Week Date Time Place Content Chapter To do
19 5/05 11:59 DEADLINE: Submit Project References Submit to Canvas before the deadline
19 6/05 8-12 SB-D209 Q&A Session 2 on Project - TAs
19 6/05
HW5 announced  
19 6/05 22:00 DEADLINE: Register for HW4 Register on Canvas before the deadline
19 7/05 8-10 HC2 Reinforcement Learning for Strategy Optimization - G. Volpe 13 Revise Notebook 13.1
19 7/05 10-12 SB-D209 Help session - TAs
19 7/05 23:59 DEADLINE: Submit HW4 Submit PDF on Canvas before the deadline
19 8/05 8-12 13-17 Sal A HW4 assessment

 

Week Date Time Place Content Chapter To do
20 13/05 8-12 SB-D209 Help session - TAs
20 13/05 22:00 DEADLINE: Register for HW5 Register on Canvas before the deadline
20 14/05 8-12 SB-D080 Q&A Session 3 on Project - TAs
20 14/05 23:59 DEADLINE: Submit HW5 Submit PDF on Canvas before the deadline
20 15/05 8-12 13-17 SB-D209 HW5 assessment
20 16/05 8-12 SB-D209 Help session - TAs
20 16/05 15:00 DEADLINE: Submit Poster Draft Submit PDF to Canvas before the deadline
20 16/05 15:15 Student Peer Review of Poster Draft Starts In Canvas

 

Week Date Time Place Content Chapter To do
21 20/05 8-12 SB-D209 Help session - TAs
21 21/05 8-12 SB-D080 Help session - TAs
21 21/05 12:00 DEADLINE: Student Peer Review of Poster Draft Ends Submit your comments in Canvas to your peers before the deadline
21 22/05 8-12 SB-D080 Help session - TAs
21 23/05 8-12 SB-D209 Q&A Session 4 on Project - TAs
21 23/05 23:59 DEADLINE: Submit Poster [for final presentation] Submit PDF to Canvas before the deadline

 

Week Date Time Place Content Chapter To do
22 26/05 8-12 SB-D080 Help session - TAs
22 26/05 15:00 DEADLINE: Submit Report Draft Submit PDF to Canvas before the deadline
22 26/05 16:00   Student Peer Review of Report Draft Starts In Canvas
22 27/05 8-12 SB-D209 Help session - TAs
22

28/05 8-12 13-17

 SB-H8 Presentation Attend the Presentation Session
22 30/05 12:00 DEADLINE: Student Peer Review of Report Draft Ends Submit your comments through Canvas to your peers before the deadline

 

Week Date Time Place Content Chapter To do
23 5/06 23:59 DEADLINE: Submit Project Report Submit PDF to Canvas before the deadline

Learning objectives

Knowledge and understanding

  • Describe the different available neural network models with their advantages and disadvantages
  • Find relevant literature to keep up with this quickly advancing field

Skills and ability

  • Implement a broad range of state-of-the-art neural network models
  • Train and validate these models 
  • Optimize these models for a specific task 
  • Plan, manage and execute a small scale project in the field
  • Write a report of their results of the project

Judgement and approach

  • Critically analyze the advantages and disadvantages of the available neural network models
  • Benchmark the results of a neural network models against other models
  • Critically evaluate and discuss advances in the field of neural networks

Link to the syllabus (Chalmers, GU)

Examination form

There will be no written final examination in this course.

The examination consists of homework assignments and a project.
Specifically, the examination is based on

  • 30% homeworks
  • 20% final project presentation
  • 50% final project report

 

Homeworks (30% of course grade)

The homework problem sets provides you with hands-on experience of advanced deep learning techniques. You are strongly encouraged to team up and collaborate on the homework assignements, to ask your classmates if you are stuck at some point, and to assist classmates in need of advice. But you must write and run your own code, and have your own work assessed.

Grading: Out of the five homeworks, you need to solve and get assessed on three homeworks.
If you get assessed on more than three homeworks, only the best three scores will be considered. [Please note that there is no requirement about the minimum number of HWs assignments that you get assessed on and no minimum threshold to "pass" the HW part of the course. For example: if you decide not to do the HWs at all, you will have a 0 score for the HW part. Still, it is possible to pass the course if you do well with the project and get an overall grade of at least 50, summing Project Presentation (max 20) and project report (max 50)]
Each homework accounts for max 10 points. Each homework is made of 4 different questions. Solving correctly: 
        1 question out of  four will give 5 points of 10
        2 questions out of four will give 7.5 points of 10
        3 questions out of four will give 9 points of 10
        4 questions out of four will give 10 points of 10

Note that it does not matter which question(s) of the homework you solve correctly, just the number. For example: 

  • Student A solves correctly question 1 of HW1: student A gets 5 points.
  • Student B solves correctly question 3 of HW1: student B gets 5 points. 
  • Student C solves correctly question 1 and 3 of HW1: student C gets 7.5 points.
  • Student D solves correctly question 2, 3, and 4 of HW1: student D gets 9 points.

Assessment:
Book a time slot for the assessment. Beware of the deadline! After the deadline is passed, you won't be able to book a time slot and you won't get assessed for that HW. No exceptions will be made. The deadlines for the HW assessment registration is indicated in the table above. The registration for a given HW assignment opens the day after the HW is announced.
Be prepared for the assessment: Generate all your figures and/or videos up front. There will be no time for running code during the assessment. Check that you have answered all questions carefully. You should be able to give reasoned answers regarding your programming choices as well as being able to discuss the implications of your results. 

 

Project

The purpose of the project work is to provide you with training in

  • Developing your own small research-style project, choosing one among the proposed topics.
  • Presenting your independent work in writing and as a poster.

The deliverables are a presentation (20% of the course grade) and a written report (50% of the course grade).

The project presentation will be on May 28, 2025. Attendance is mandatory.

The final written report is due by June 5, 2025. No late reports will be accepted.

General information

The project topics (see: Files > Project Topics: https://chalmers.instructure.com/courses/34272/files/folder/Project%20topics)  are proposed to the students by the TAs.
Each student must register to one (and only one) of the topics. Registration happens through Canvas, on a "first come-first served" basis.
Deadline to register to a project topic: 4 April 22:00.

Each student must then choose whether to conduct their project individually (1 person team) or in a team of 2, 3 students in total.  The teams are self-organized by the students and must be formed among the students signing up for the same topic. If you are going to do a 2-, 3-, students project, you must agree this with the other students and communicate your group to the course examiner before 11 April at 16:00. If you have signed up for a project topic but you have not communicated you are in a team, then we consider that you are working individually.

These are the possible configuration for the project:

  • 1-person project -> Final report: 5 pages (exact number of pages, including 5-10 references)
  • 2-people project -> Final report: 9 pages (exact number of pages, including 10-20 references)
  • 3-people project -> Final report: 13 pages (exact number of pages, including 15-30 references)

Please note that, after communicating the arrangement, no change to the report size will be made even if some students drops out of a group. For example: three students agree to work together, but one drops out — the two remaining students will have to submit a 3-people project report, as they have committed to do.

Formats and Templates

  • The format for the poster is: PDF, portrait. There is no compulsory template.
  • The template for the final report is found here: add link. It is compulsory to use the provided template with no further style customization. The points for the different parts of the project are provided in the template.

Deadlines

  • 4 April, 22:00: Project Registration closes
  • 11 April, 16:00: Communicate before this deadline if choosing a 2-people or a 3-people project (no communication due if you choose to work individually).
  • 22 April, 12:00: Project Abstract and Methods Overview due
  • 5 May, 12:00: Project Relevant References due
  • 16 May 15:00: Poster Draft due
  • 21 May 12:00: Peer-review of Posters Draft of assigned students due
  • 23 May 23:59: Poster (final, for presentation) due
  • 26 May 15:00: Project Report Draft due
  • 28 May 8-12 and 13-17: Project presentation (compulsory for all students)
  • 30 May 12:00: Peer-review of Project Report Draft of assigned students due
  • 5 June 23:59: Project Report (final) due

Project Q&A Meetings

After committing to a project topic, you will have to develop your own project question and direction. As a support in carrying out your project, you have:

  • Possibility to discuss with the other peers choosing the same project topic [consider those peers as a discussion group].
  • Possibility to ask project-related questions to a TA during four Q&A sessions (23 April, 6 May, 14 May, 23 May)

 

Poster presentation (20% of course grade)

The presentation of the project should clearly show what you have done.
Put the emphasis on what your problem formulation is, a general discussion about how you tackled it, what problems you had, and what your conclusions are.

Checklist for poster presentation

When preparing your poster, consider the following guidelines:

  • Structure: Is the poster well structured?
  • Clarity: Is it clear from the presentation what is being investigated?
  • Format: Does the presentation fit the requested format? (i.e.: PDF, portrait, well readable when printed in A3 format.)
  • Motivation: Is it explained well why the project is important? 
  • Conclusion: Are conclusions and implications clear? 
  • Methods: Are the methods explained sufficiently but not excessively?
  • Presentation quality: Is the poster engaging and visually appealing?

 

Criteria for evaluation of Poster presentation

  • Interactive Engagement in Poster presentation [0-4 points]: During the poster presentation: you need to visit the various posters and ask questions. You need to write write down on the Q&A sheet (provided during the poster session) the questions you ask and the relative answer you receive. You need to annotate at most 1 question+answer per poster visited. You will get 0.5 points for each question+answer, with a maximum of 4 points.
  • Peer-Review Engagement [0-4 points]: You will be assigned two other projects to Peer-Review (poster draft). During the peer-review, you should submit a substantial comment to each poster draft, showing that you have read it. You should give 5 comments for improvement. If your comments are substantial, you will receive 2 points for each comment submitted. Maximum 4 points in this part.
  • Poster evaluation [0-12 points]: You will receive max 2 points for each the following criteria:

               * Structure: Does the poster have a title, list of authors, affiliation?
               * Clarity: Is it the take-home message clearly identifiable in the poster?
               * Format: Does the presentation fit the requested format? (i.e.: PDF, portrait. When printed in A3 format, should be readable, i.e., minimum fontsize 11pt.)
               * Motivation: Is it explained why the project is important? 
               * Conclusion: Is there a clearly identifiable conclusions statement? 
               * Methods: Are the methods explained sufficiently but not excessively?

 

Report (50% of course grade)

The report should be written according to the template provided. Link to the directory with the template files: https://chalmers.instructure.com/courses/34272/files/folder/Project%20Template .

Structure your report like a scientific article, with an abstract summarising the rationale and results of the project; an introduction shortly explaining its background and motivating why the question is interesting; methods and/or results section(s) describing an overview of the available models for the task, your model and what you do with it; a result and discussion section; and ending with a conclusion. Put some work into the discussion and conclusion sections. This is where you demonstrate that you truly understand the implications of your work, including shortcomings and uncertainties. It is important that the discussion does not fall out as a simple summary of what the figures show.

Write in plain language and write enough to say what you need to say. Don't think "the report feels short, better throw in some extra figures." If you can say the same thing in fewer words, do so.

Be sure to reference any source you use. The report should be readable and understandable on its own, but there is no need to reproduce for example derivations of equations from your sources; a citation is enough.

Figures are an important part of the report, but only those that substantially contribute to your analysis should be included. Make sure that each figure is well designed with informative captions (not just "Fig. X shows how quantity A depends on quantity B"). If you find it hard to do this, you probably are not clear on why you include an figure, so cut it out.

Most importantly, use your own judgement and try to write a report you would like to read.

Checklist for project report

When preparing your project report according to the provided template, consider the following guidelines:

  • Structure: Is the project report well structured, i.e., conformal to the project template?
  • Motivation: Does the project have a clear research question?
  • Background: Is the background of the research question well explained, including references to the literature?
  • Overview: Does the overview consider possible methods, explain their use case scenario, discuss their features with advantages and disadvantages, with references to the literature?
  • Methods: Are the methods explained adequately? Is the analysis appropriate for convincingly answering the research question?
  • Execution: Does the project answer the initial or iterated research question?
  • Figures: Are the figures included informative with descriptive captions? Are the figures referenced in the text?
  • Format: Have you used the provided template?
  • Outlook: Are the implications of the results clearly stated?
  • Contributions, Conflict of Interest, Data and Code availability : Are such statements included in the report? 

Note that the report template contains the maximum points that can be obtained for each part.

Note also that the research question does not have to be answered in the affirmative. A negative result is equally valid as long as an analysis is carried out that properly explains the negative result and what eventually would work better. 

 

Criteria for evaluation of Project Report

  • Peer-Review Engagement [0-6 points]: You will be assigned three other projects to Peer-Review (project report draft). During the peer-review, you should submit a substantial comment to each report draft, showing that you have read it. You should give 5 comments for improvement. If your comments are substantial, you will receive 2 points for each comment submitted. Maximum 6 points in this part.
  • Project evaluation [0-44 points]: Check the project report template to see the maximum points assigned to the different parts of the report. Also, you will find there all the information about the requirements on number of pages, figures, references, and other important details of the grading.

 

Calculation of final grade

You can get at most 30 points from the homework and 70 points from the project. The maximum combined score is 100.

The grade limits will be 50 points for grade 3, 70 points for grade 4, and 90 points for grade 5.

For GU the limits will be 50 points for G and 80 for VG.

Course summary:

Date Details Due