Course syllabus
News
November 10. Tentagranskning on Tuesday November 16 in PJ salen (Origo building) between 9:00 and 10:00.
November 9. The exam results will be announced on Monday November 11. Here's the exam, and here are the solutions.
October 19. Exam revision: you can skip Chapter 11 (reinforcement learning). This will not be in the written October exam.
October 19. Suggested exercises for Chapters 10 & 11: 10.3, 11.1 . Continuously updated solutions to selected exercises are available in Files/Solutions. Solutions are labelled by the date they were made available. Not all exercises have official solutions. While reading the solutions you should ignore the "Lecturer endorsement" note, it is irrelevant.
October 13. Reading list for week 8. Chapter 11. Exercises for week 8: old exams here (partial solutions), here (solution), and here (solution).
October 11. Reading list for week 7. The first lecture on October 12 is reverse classroom (read Chapter 8, and ask questions during this lecture). Chapter 10. Exercises for week 7: old exam. Solution: solution_exam_26_October
September 30. Reading list for week 6. Chapter 9. Exercises for week 6: 9.5, 9.6, 9.8.
September 23. Reading list for week 5. Chapters 7 and 8 in the book. Finish HW2 and solve exercises 7.2, 7.4, 7.5, 7.7, 8.1, 8.3, 8.6 in the book.
September 20. Machine learning for active matter. Summer-school lecture I've given today.
September 17. Reading list for week 4. Chapter 6 and Sections 7.1 and 7.2 in the book. Work on HW2 in OpenTA. Solve exercises 6.2, 6.4, 6.6 & 6.9 in the book.
September 16. You find the video recordings of the lectures in the CANVAS Calendar. The most recent lectures use Chalmers Play.
September 14. Reading list for week 3. Chapters 4 and 5 in the book. Complete homework HW1 in OpenTA (due September 17). Solve exercises 4.4, 4.6, 5.2, 5.6, 5.7 & 5.8 in the book.
September 3. Reading list for week 2. Chapters 1 - 3 and 4.1 and 4.2 in the book. Start to work on homework problems in OpenTA (due September 17). Solve exercises 2.4, 2.9, 2.13, 3.2, 3.4 & 4.3 in the book.
August 31. The first lectures are online, via zoom. You can find the zoom links in the Calendar, or just click on the items in the course summary below.
Note. The reading lists are preliminary.
Course representatives
Arash Darakhsh Mobarekeh darakhsh at student.chalmers.se
Ida Ekmark ekmark at student.chalmers.se
Kaver Hui kaver at student.chalmers.se
Kaize Felipe Deng Ying
Subramanya Mallappa
Welcome
Welcome to Artificial Neural Networks 2021. How to prepare? Login to the online system OpenTA (for the link see menu on the left) to do the preparatory maths exercises. Login to discussion forum and pose any OpenTA questions there. See you at the first zoom lecture on Tuesday 31 August.
Link to discussion forum.
Link to preliminary schedule in Time Edit, see also course summary below.
Introductory slides. Link.
Format
Zoom lectures and exercises during the first week(s). Each event has a different zoom link. Go to the Calendar to find the link. These lectures will be recorded and they'll be available here on CANVAS. If regulations allow, we'll teach some of the later lectures and exercises in person in class, and stream them at the same time. If possible, these lectures will also be recorded.
Important dates
First lectures on Tuesday August 31 via zoom. Let's login to the zoom room at 13:00, to test that everything works, so that we can start on time at 13:15.
Deadline homework problem 1: September 17 (2021)
Deadline homework problem 2: October 1 (2021)
Deadline homework problem 3: October 22 (2021)
Exam: October 25 (2021)
Contents
1. Introduction
Part I Hopfield models
2. Deterministic Hopfield networks
3. Stochastic Hopfield networks.
4. The Boltzmann distribution
Part II Supervised learning
5. Perceptrons
6. Backpropagation
7. Deep learning
8. Convolutional networks
9. Recurrent networks
Part III Learning without labels
10. Unsupervised learning
11. Reinforcement learning
Course book
B. Mehlig, Machine learning with neural networks, Cambridge University Press (2021).
Further literature
I. Goodfellow, Y. Bengio & A. Courville, Deep Learning, MIT Press
Examination
Credits for this course are obtained by solving the homework problems (solutions of examples and programming projects) and by a written examination. There are three sets of homework problems. Each of the three gives at most 4 points. The exam gives at most 12 points, resulting in a maximum of 24 points.
To pass it is necessary to obtain at least 5 points in the written exam, and to have at least 14 points in total.
Passing grades:
Chalmers: 3: >13.5p; 4: >17p, 5: >21.5p
GU: G: >13.5p; VG: >19.5p
ECTS: C: >13.5p; B: >17p; A: >21.5p
OpenTA
This course uses the OpenTA online system developed by Stellan Östlund and Hampus Linander for exercises, homework, and exam preparation.
Rules for homework submissions
Same rules as for written exams apply: it is not allowed to copy any material from anywhere unless reference is given. All students must write their own computer programs and submit their own solutions. All submissions are handled via OpenTA. For all homework sets, your program code must be uploaded to OpenTA.
Keep a backup of your solutions to the OpenTA questions, of your submitted PDF files as well as the answers you typed in. The system does not store your answers after December 2021. If you take a re-exam in January or August 2022 you will be asked to re-submit all answers and OpenTA scores.
Your OpenTA points are valid for the two re-exams in January and August 2022. Please contact any of the teachers if you need guidance for your exam preparation, or if you have questions about the coming re-exams. To pass the course in future academic years (for instance 2022/2023) you need to redo the OpenTA problems for that academic year.
URKUND. For each homework, concatenate the PDF files you uploaded to OpenTA, and send the PDF file electronically to Bernhard.Mehlig.chalmers@analys.urkund.se. Further instructions for the email to URKUND: Subject = [FFR135] (Chalmers) or [FIM720] (GU). Attach the PDF file with filename firstname-lastname-hw1.pdf for the first homework. For each homework, submit a single PDF file only. Note: it is not possible to retract files from URKUND, neither is it possible to correct your submission. Only one submission per homework, otherwise you may alert the plagiarism software. Information about the URKUND system can be found here.
For Homework 3 you will submit your solutions as PDF files to OpenTA. The format of the solutions must be as follows. There are four questions giving 1p each. Separately for each 1p-question you must submit at most one A4 page with 12pt single-spaced text, and with 2cm margins. LateX template. Each page may contain at most one Figure and/or one Table with the corresponding Figure and/or Table caption, in addition to the text discussing the results shown in the Figure/Table. It is not necessary to write a full page for each problem, but you must explain/describe what you have done and clearly state your answers/results to the questions and your conclusions. When necessary you must discuss possible errors and inaccuracies in your results. If you are asked to plot results/make graphs, you do this in a Figure with legible axis labels and tic labels. All symbols and lines must be explained in the Figure or in a caption. The Figure may consist of separate panels. Refer to them as 'left panel', 'right panel', 'bottom panel', etc. (or alternatively label them 'a', 'b',...).
Deadlines (see above) are sharp. Late submissions are not accepted.
Homework 1. Hopfield model.
Homework 2. Backpropagation.
Homework 3. Deep-learning/reinforcement-learning project.
Written exam
The exam covers the material in the most recent version of the lecture notes as well as in the homework problems. Old exam questions are given in the lecture notes (link on CANVAS).
Date for written exam, deadline for registration for exam. Please see this link. Course code FFR135.
If date & time of the exam collide with another exam you must take, then you must follow the steps outlined here.
If you don't pass the exam
Your OpenTA points are valid for the two re-exams in January and August 2022. Please contact any of the teachers if you need guidance for your exam preparation, or if you have questions about the coming re-exams. To pass the course in future academic years (for instance 2022/2023) you need to redo the OpenTA problems for that academic year.
Course summary:
| Date | Details | Due |
|---|---|---|