The tutorials for the course Neural Networks, Machine Learning and Randomness are held on odd weeks on Wednesdays (there are some exceptions, exact dates bellow) from 11:0 to 12:30 and from 12:45 to 14:15 (two parallel groups) in room T9:350.
credit
In order to be able to take the exam, you have to attend the tutorials and actively participate in them. There is no strict limit on attendance, contact me if you will have missed multiple tutorials.
Additionally, you have to submit a semester project. The project should cover some of the topics of the lectures or tutorials and apply them in practice and should consist of some experiments and a report (either as a Jupyter notebook or separately). The topic of the project should be agreed with me in advance. Generative AI usage is allowed for code and report writing but the overall idea, experiment design and interpretation must be the students work. If any generative AI was used, its usage must be described in the report. After submitting the project, you will have to schedule a short call with me to discuss the project and answer some questions about it. After that, the project will be awarded 0-70 points. Finishing the project is a prerequisite for taking the exam.
study materials
The exercise materials are in the form of Jupyter notebooks using Python. For easy installation of Python, Jupyter, and the required packages, we will use uv . The first exercise is intended to familiarize you with this technology. To replicate the exact environment in which the notebooks were created, you can use the files pyproject.toml and uv.lock.
| # | date | name | topics | assignment | solution |
|---|---|---|---|---|---|
| 1 | 2026-10-05 | introduction to machine learning | basics of machine learning in Python, supervised, unsupervised, reinforcement, self-supervised learning, linear regression, cost function, visualizing the regression line, evaluating simple models | notebook | notebook |
| 2 | 2026-10-07 | perceptron and logistic regression | logistic regression, binary classification, cost function, implementation and visualizitaion of the decision strategy, perceptron, its learning algorithm and implementation | notebook | notebook |
| 3 | 2026-10-21 | dimensionality reduction and clustering | principal component analysis, dimensionality reduction and its mathematical concepts (SVD), visualizing data with PCA, k-means clustering, clustering metrics | notebook | |
| 4 | 2026-11-18 | decision trees | decision trees, random forrests, their construction, splitting criteria and implementation | ||
| 5 | 2026-12-02 | bayesian methods | bayes theorem, maximum likelihood estimation vs. maximum a-posteriori estimation, naive bayes classifier vs. k-nearest neighbor classifier | ||
| 6 | 2026-12-16 |