PLIN081 Advanced machine learning methods

Faculty of Arts
Autumn 2024
Extent and Intensity
0/2/0. 4 credit(s). Type of Completion: k (colloquium).
Taught in person.
Teacher(s)
Mgr. Richard Holaj, Ph.D. (lecturer)
RNDr. Jan Rygl (lecturer), Mgr. Dana Hlaváčková, Ph.D. (deputy)
Guaranteed by
Mgr. Richard Holaj, Ph.D.
Department of Czech Language – Faculty of Arts
Contact Person: Bc. Silvie Hulewicz, DiS.
Supplier department: Department of Czech Language – Faculty of Arts
Prerequisites
PLIN080 Intro. to quant. ling.
Email to the instructor introducing oneself, previous programming and artificial intelligence experience, future career aspirations, and the envisioned role of machine learning in one's career.
Setting up necessary tools: Creating a personal account on GitHub.
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
The capacity limit for the course is 14 student(s).
Current registration and enrolment status: enrolled: 0/14, only registered: 0/14, only registered with preference (fields directly associated with the programme): 0/14
fields of study / plans the course is directly associated with
Course objectives
Deepening knowledge of programming in Python and getting acquainted with the use of ML focused on NLP in an environment simulating work in a company:
- Team Collaboration
- Code Testing
- Code Review Practices
- Adaptive Project Management
- Big Data Processing, particularly in English - Project Difficulty Estimation
Learning outcomes
Students after completing the course:
- will have a better idea about the implementation of ML projects in small companies;
- deepen their knowledge of programming in Python;
- gain more experience with team collaboration in commercial environments;
- will have basic experience with estimating the difficulty of projects.
Syllabus
  • Forming teams and setting up an environment for effective collaboration.
  • Solution architecture, prototyping and automated tests setup.
  • Processing and working with big data.
  • Creating simple REST APIs and communicating with the client.
  • Experimenting with ML algorithms and evaluating them.
  • Negotiating project goals and acceptance metrics.
  • Accelerating code and writing documentation.
  • Containerizing solutions using Docker technology.
Teaching methods
Discussion, Team Project Work, and Commercial Environment Simulation.
Assessment methods
Team projects:
- algorithmics and efficiency (10 points);
- code style and code readability (10 points);
- quality of code reviews (10 points);
- team work (10 points);
- functionality according to specifications (20 points);
- final team defence of the project (40 points).

A minimum of 60 points is required for successful completion of the course, including at least 10 points from the final defense. Extra points can be earned during the course.
Language of instruction
Czech
Further Comments
The course is taught: every week.
Teacher's information
https://github.com/aicheck-tech/PLIN081
  • Permalink: https://is.muni.cz/course/phil/autumn2024/PLIN081