Course code InfT5050

Credit points 4

Data science and machine learning algorithms

Total Hours in Course160

Number of hours for lectures24

Number of hours for seminars and practical classes24

Independent study hours112

Date of course confirmation06.09.2022

Responsible UnitDepartment of Computer Systems

Course developer

author Datoru sistēmu katedra

Vitālijs Komašilovs

Dr. sc. ing.

Course abstract

The aim of the study course is to learn the practical aspects of machine learning. The course will start with a study of preprocessing and visualization techniques for data analysis. Then, a review the most common algorithms for supervised and unsupervised learning. It will also include an introduction to Deep Learning.

Learning outcomes and their assessment

As a result of learning the course, students:
• knows the theoretical aspects of machine learning algorithms - theory tests;
• have practical skills to work in data-based projects - practical works;
• are able to use modern scientific libraries (for example, NumPy, Pandas or Scikit-learn) - practical works;
• acquires the competence to work with data analysis and visualization tools - practical work

Course Content(Calendar)

This is a schedule for lecture topics [L] and practical topics [P]:
1. [L] Introduction to Machine Learning. [L/P] How to install and use Jupyter and IPython notebooks – 2 h.
2. [P] numpy tutorial. [L] Data exploration – 4 h.
3. [P] pandas tutorial I. [P] pandas tutorial II – 4 h.
4. [P] Tools for data visualization (matplotlib and seaborn) – 2 h.
5. Data analysis test and practical assignment – 2 h.
6. [L] Lineal regression. [L] Logistic regression -2 h.
7. [L] Validation and regularization. [P] Introduction to scikit-learn – 4 h.
8. [L] Supervised learning models. [L] Ensembles – 4 h.
9. [P] Validation and pipelines in scikit-learn. [P] Example of supervised learning – 4 h.
10. [L] Unsupervised learning. [P] Example of unsupervised learning – 4 h.
11. Machine learning test and practical assignment – 2 h.
12. [L] Introduction to Deep Learning. [P] Introduction to Google Colab and keras – 4 h.
13. [L] Basics of neural networks. [P] Implementation of dense networks - 4.
14. [L] Convolutional Neural Networks. [P] CNNs in keras – 4 h.
15. Deep learning test and practical assignment – 2 h.

Requirements for awarding credit points

Students are awarded credit points with a final positive mark. To get a positive final mark, the students must pass all the practical assignments and obtain a positive mark as an average mark of the tests (30%) and practical assignments (70%).

Description of the organization and tasks of students’ independent work

There will be three assignments for the students to work independently. The students will have a week to analyze each practical assignment and start their work on it. Each assignment will be due two or three weeks after it is published, depending on its difficulty.

Criteria for Evaluating Learning Outcomes

Final mark will be calculated as an average mark of the tests (30%) and the practical assignments (70%). To get a passing mark, students must also receive a passing mark in each practical assignment.

Compulsory reading

1. Russell S.J., Norvig P. Artificial intelligence: a modern approach. Malaysia: Pearson Education Limited, 2016.
2. Mitchell T. Machine Learning. New York: McGraw-Hill, 1997.
3. McKinney W. Python for Data Analysis. Beijing: O’ Reilly, 2013.

Further reading

1. Grus J. Data Science from Scratch. Beijing: O’ Reilly, 2015.
2. Han J., Kamber M. Data mining: concepts and techniques. 2nd ed. San Fransisco: Morgan Kaufmann; Amsterdam [etc.]: Elsevier, 2006. 770 p.

Periodicals and other sources

MOOC course on Machine Learning. Pieejams:


ITF Master's study program “Information Technology”