LV EN RU DE FR

Building Machine Learning Models Using Python

Prior knowledge

InfT3049, An Introductory Course in Artificial Intelligence

Course abstract

This course of study aims to provide students with an in-depth understanding of artificial intelligence (AI) and machine learning. To teach students how to build machine learning models using the Python programming language and open source software libraries, and to apply this knowledge to building solutions across industries.
The study course is learned independently, using the e-study in the learning materials posted on the portal, which consist of theoretical materials (lectures) and practical works (assignments) and tests.

Learning outcomes and their assessment

Knowledge:
- in-depth understanding of Artificial Intelligence (AI) and Machine Learning, including the algorithms and techniques used in these fields;
- knowledge about the Python programming language and open-source software libraries that are commonly used for machine learning.
Skills:
- the ability to use Python and open-source libraries to create machine-learning models and solve problems in various fields;
- the skill to assess which problems can be solved using Artificial Intelligence, and to choose appropriate algorithms and techniques to tackle these problems.
Competencies:
- competency to apply their knowledge of AI and Machine Learning to develop solutions for real-world problems in various domains;
- competency to work with machine learning models and develop solutions to complex problems in a variety of settings.

Course Content(Calendar)

Topic Number of hours (academic hours)
Lecture Independently work
1. Introduction to Machine Learning; 1 h; 1 (Self-check test) h
2. Python Application in Data Science ; 8 h; 1 (Self-check test) h
3. Scikit-learn Library ; 18 h; 2 (2 Self-check tests) h
4. Developing a Machine Learning Model ; ; 5 h (Assignment)
5. Developing a Machine Learning Model ; ; 5 h h(Assignment)
6. Tensorflow Basics for Deep Learning ; 6 h; 2 (2 Self-check tests) h
7. Developing a Machine Learning Model ; ; 14 h (Assignment)
8. Developing a Machine Learning Model ; ; 15 h (Assignment)

9. Final Test; ; 2 h

Requirements for awarding credit points

In order for the study course to be counted as successfully completed:
1) The student must submit at least 80% of all practical work - self-check tests and practical work. The self-check test is considered submitted if the student has answered at least 70% of the questions correctly.
2) Successful completion (at least 65%) of the final exam in test format.
If the student has not submitted at least 80% of the practical work, he is not admitted to the final test.

Description of the organization and tasks of students’ independent work

The study course is learned independently, by the student, using the materials added to the e-study portal.
The student follows the attached course plan, which describes both the order in which the lectures of the study course must be studied and the tasks to be completed after the lecture.
After certain lectures, the student must complete self-check tests, which are attached to the study course and available on the e-study portal. The self-check tests are designed in such a way that the student can check his knowledge after learning the theory on the specific topic.
In addition, during the study course, the student has to do practical work. Descriptions of the tasks of the practical works are attached and available on the e-study portal. The student completes online using free programs such as Jupyter Notebooks and Tensorflow.

Criteria for Evaluating Learning Outcomes

The completion of a study course is evaluated with a pass/fail grade. To pass the course, the student must complete at least 80% of all practical work and successfully pass (at least 65%) the final exam in a test format.

Compulsory reading

Stuart Russell,Peter Norvig. Artificial Intelligence: A Modern Approach (4th Global ed.), Pearson Education, 1168pp., 2021. ISBN: 9781292401133
Aurélien Géron. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (2nd Edition). O'Reilly Media, Inc., 600 pp., 2019. ISBN: 9781492032649
Sebastian Raschka. Machine Learning with PyTorch and Scikit-Learn. Packt Publishing Ltd., 770 pp., 2022. ISBN: 9781801819312
https://inria.github.io/scikit-learn-mooc/index.html
https://learn.microsoft.com/en-us/training/paths/tensorflow-fundamentals/
https://www.javatpoint.com/machine-learning
https://scikit-learn.org/stable/user_guide.html

Periodicals and other sources

https://www.udemy.com/course/complete-machine-learning-and-data-science-zero-to-mastery/
https://developers.google.com/machine-learning/glossary

Notes

Elective course for bachelor programmes.