Video about organisational information (18 min), slides
Video about what course this is (10 min), slides
Lecture 01 - Introduction (watch before practice sessions Sept 8-10)
Lecture 02 - First look at the data (watch before practice sessions Sept 15-17)
First look at an attribute:
Video (48 min), slides
Distribution of attributes:
Video (45 min), slides
Lecture 03 - Data visualization (watch before practice sessions Sept 22-24)
Video (1h 45min), slides -- This lecture is by Raivo Kolde, Associate Professor of Health Informatics.
Optional additional material - Tableau and visualisation: Video 1, video 2
Lecture 04 - Frequent pattern mining (watch before practice sessions Sep 29-Oct 1)
Lecture 05 - Relations of attributes, clustering and dimensionality reduction (watch before practice sessions Oct 6-8)
Relations of attributes:
Video (27 min), slides
Clustering:
Video (42 min), slides
Dimensionality reduction:
Video (21 min), slides
Lecture 06 - Introduction to machine learning (watch before practice sessions Oct 13-15)
Example prediction task: Lenses:
Video (7 min), slides
Supervised learning terminology:
Video (3 min), slides
Majority class classifier:
Video (4 min), slides
Decision tree learning:
Video (33 min), slides
Classification with K nearest neighbours:
Video (4 min), slides
Example: hand-written digit recognition:
Video (6 min), slides
Curse of dimensionality:
Video (4 min), slides
Lecture 07 - Machine learning 2 (watch before practice sessions Oct 20-22)
Example: Decision tree on image data:
Video (6 min), slides
Random forest:
Video (4 min), slides
Example: Random forest on image data:
Video (6 min), slides
Example: state of water:
Video (11 min), slides
Linear classification and support vector machine:
Video (15 min), slides
Underfitting and overfitting:
Video (12 min), slides
Hyperparameter tuning and cross-validation:
Video (11 min), slides
Machine learning pipeline:
Video (3 min), slides
Learning on imbalanced data:
Video (13 min), slides
Lecture 08 - Machine learning 3 (watch before practice sessions Oct 27-29)
Tradeoff between true positives and false positives:
Video (8 min), slides
Scoring classifiers and ROC curves:
Video (19 min), slides
What is regression?
Video (5 min), slides
Linear regression:
Video (11 min), slides
Regularisation and regression:
Video (19 min), slides
Lecture 09 - Machine learning 4 (watch before practice sessions Nov 3-5)
What is deep learning:
Video (25 min), slides
Training neural networks:
Video (33 min), slides
Convolutional neural networks:
Video (5 min), slides
Machine learning landscape:
Video (14 min), slides
Organisational information and suggested topics for projects
Please see the project information page
Lecture 10 - Computational statistics (watch before practice sessions Nov 17-19)
Sample and population:
Video (9 min), slides
Example task with red and black cards:
Video (26 min), slides
Histogram on a sample vs population:
Video (13 min), slides
Some statistical terminology:
Video (13 min), slides
Optional additional material (not tested at the exam)
If you are interested in how recommendation systems work, then here is a short lecture by Yan-Martin Tamm, a junior researcher at the University of Tartu:
- Recommender Systems - video (31 min)
If you would like to understand what vector embeddings are, and how to build a chatbot that uses a vector database to answer user queries, then look at these videos by Shaw Talebi:
- How to Improve LLMs with RAG - video (21 min)
- Text Embeddings, Classification, and Semantic Search - video (24 min)
These videos by Shaw Talebi are part of a longer series.