Welcome to the GitHub repo for the introduction course in Introduction to Machine Learning at Uppsala University. This repo contains all necessary material and information for the course.
The course is given to second-year master students in the Statistics masters program.
The course takes roughly 20h per week. In total the course should take roughly 200h. If the student aims for VG more time might be needed.
See course syllabus here.
Roughly the course assumes basic knowledge in linear algebra, calculus, probability theory and programming (with R or Python).
See the R setup instructions before using TensorFlow and Keras.
You can find a rough course plan with reading instructions here.
You can find the course schedule on TimeEdit here (search for course code 2ST129).
The course is graded with U (Underkänd/Fail), G (Godkänd/Pass), VG (väl godkänd/Pass with distinction).
To pass, you should pass all written assignments, the oral exam for each assignment, and the mini-project.
To get the grade VG on the course, a total of 7 or more VG points is needed. Each assignment has an additional task to complete to get VG on the assignment (and one VG-point). To receive that point, you must also pass the oral exam for the assignment without a failed attempt. Missing an oral examination opportunity does not remove VG eligibility. If the final mini-project gets VG, the students are awarded 2 VG points for the mini-project. The existing first-deadline requirement for the written assignment still applies; the oral exam may be taken at a later examination opportunity.
Note that aiming for VG might mean that you need to put in more hours than the expected 20h per week.
Each assignment is additionally examined through an oral exam. You may be examined on one to three assignments per examination session, chosen from the written assignments you have already submitted in Studium. See the oral exam instructions and questions for the full rules and all eight assignment question banks.
Optional seminars provide practice in oral explanations and short derivations in groups of three. Before a seminar, choose two questions from the oral exam question list that you find difficult. Take turns as explainer, questioner, and checker, aiming to work through 3–6 questions per group, with help from a TA. See the seminar instructions (PDF) for details.
Grades are not subject to appeal. However, a grading decision must be reassessed if it is clearly incorrect. Grades can never be lowered. If students want grades to be reassessed, they should contact the course administration who will distribute a form for reassessment the students have to fill out.
If you fail or drop-out from the course you will need to re-take all assignments and redo the mini-project next time the course is given.
Below are the main references for the course. All books are available free online. Some articles may need access from an Uppsala University network.
- BB: Bishop, Christopher M., and Hugh Bishop. Deep Learning: Foundations and Concepts. Springer, 2024. online access
- ESL: Hastie, Trevor, Tibshirani, Robert, and Friedman, Jerome. The elements of statistical learning: data mining, inference, and prediction. 2nd Edition. Springer Science & Business Media, 2009. online access
- DLR: Chollet, François, and Joseph J. Allaire. Deep Learning with R. Manning, 2018. online access
- Sutton, R. S., and Barto, A. G. Reinforcement learning: An introduction. MIT Press, 2020. online access
In addition, the following material will also be included (note that you might need to access the material through the Uppsala University network):
- Ruder (2016). An overview of gradient descent optimization algorithms. online access
- Efron (2020). Prediction, Estimation, and Attribution. Journal of the American Statistical Association, 115(530), 636-655. online access Note! You need to be on the Uppsala University network to access the article.
- Kingma DP and Welling M. An Introduction to Variational Autoencoders, 2019. online access
- Alammar, J. The Illustrated Transformer, 2018a. online
- Alammar, J. The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning), 2018b. online
- Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł. and Polosukhin, I., 2017. Attention is all you need. In Advances in neural information processing systems (pp. 5998-6008). online
- Griffiths, M. and Steyvers. 2004. Finding Scientific topics online
- Blei, D. 2012. Probabilistic Topic Models online
- Verma, S. and Rubin, J. (2018) Fairness definitions explained. online
- Zhao et al (2023) A Survey on Large Language Models online
The literature list might change slightly during the course.
- Chen, T. (2016) XGBoost: A scalable Tree Boosting System online
- ISLV: Hastie and Tibshirani, Statistical Learning with R (Video material) online access
- 3B1B1: Three Blue One Brown on Neural Networks online access
- 3B1B2: Three Blue One Brown on Convolutions online access
- Dirac, L. (2019) LSTM is dead! Long live Transformers. online access
- Ng, Andrew (2017) One convolutional layer. online access
- Hand, Paul, Variational Autoencoders online
- Phi (2020) Illustrated Guide to Transformers Neural Network: A step by step explanation online
- UnHeard (2023) Nick Bostrom: How AI will lead to tyranny online
- Read the literature according to the rough course plan
- Watch the videos to get more indepth knowledge/understanding (however, optional)
- Do the assignment
Online course discussions will be held through Slack. See Studium for details on how to log in.
The course will have 2 guest lectures that the guest lecturers will give through Zoom. Otherwise, the course will be held on campus. You can find information and support for students on Zoom here.
Main Teacher: Måns Magnusson Teaching assistant: Hannes Waldetoft
The course consists of rougly 8 blocks (weeks) of material. Each week consists of the following (expected workload in parenthesis):
- Two lectures/computer labs (approx. 3h per week)
- Online video material and reading assignments (approx. 4h per week)
- An individual computer assignment (approx. 14–16 hours per week)
Each week an individual computer assignment is done with a focus on implementing the main part of the material. Each assignment is completed individually and should follow the computer assignment template.
Every assignment report must also include one oral exam question of your own and a short model answer. The question should concern the assignment or its associated reading or lectures, be suitable for a 2–4 minute oral answer, and test conceptual understanding rather than only calculation or code. It must not already be in the oral exam question list or be very close to an existing question, for example by only changing numbers. You are not allowed to use large language models, such as ChatGPT, at all for this contribution. State Yes or No to whether course staff may use or adapt your question and answer in a future oral exam. See the assignment instructions and report template for the required format.
You may use large language models (LLMs), such as ChatGPT, like you may discuss with fellow students: to learn, ask for explanations, and get feedback. You may not use LLMs to produce the solution you submit. You must be able to explain every part of your own assignment at the oral exam, including your code, results, and reasoning, even when it is not covered by the published oral exam questions. If course staff have concerns about your understanding or the authorship of any part of your submission, you may be asked to explain that part at the oral exam.
For optional study support, start a new conversation by uploading or pasting the AI tutor instructions and asking the tool to follow them. You may then upload the full teacher-provided assignment instructions, including supplied example code, and ask for explanations, incremental hints, and separate practice examples. Do not upload your own report, answers, or assessed code. Loading the tutor instructions does not guarantee that the tool will follow them: you remain responsible for keeping your submitted work your own. Do not ask the tutor to help with the original oral-exam-question contribution, even though its instructions appear in the assignment.
Where an exercise explicitly asks you to run an LLM and report its output, you may do so for that experiment. Your explanations and analysis must be your own. This permission does not apply to the oral-exam-question contribution.
Students should return the computer assignments no later than Sunday 23.59 each week. For a detailed list of deadlines, see the rough course plan.
There are two complementary turn-ins of assignments, the last day of the course and roughly 2-4 weeks after the course ends. After the last possible time to turn in the assignment no more chances will be given. In this case, you will be failed on the course and you will need to retake the course next year.
Each assignment will be graded and evaluated within 10 working days.
To pass the assignment 75% of the points are needed. Similarly 75% of the VG assignment is needed to get a VG-point.
A guest lecture will be given on AI and ethics by Karim Jebari and Holli Sargeant.
The last two weeks will focus on a course project where 2-3 students choose their data and create a supervised machine learning predictive model for a real-world dataset.
You can find details and instructions on the project work here. An example report from a previous course (2025) can be found here. Note that there can be new instructions since 2026, so see the example rather as an inspiration and example.
Frequently asked questions will be collected here.