Course detail

Machine Learning Fundamentals

FEKT-MPA-MLFAcad. year: 2023/2024

The course deals with both the classical machine learning methods such as support vector machines or principal component analysis and the machine learning techniques based on the neural networks, including convolutional and recursive networks. The concept of quantum computation and related algorithms is also introduced. Besides the lectures, the computer labs represent a very important part of the course, and serve as a tool to understand the basic principles of methods and their usage in communications.



Language of instruction


Number of ECTS credits


Mode of study

Not applicable.

Offered to foreign students

Of all faculties

Entry knowledge

A student who enrolls in a course should:
- understand basic mathematical methods at the bachelor's degree level
- be able to write a simple program in the Matlab environment and one of the higher programming languages


Rules for evaluation and completion of the course

Grading of MPA-MLF in academic year 2023/24

PC labs attendance, homeworks, reports:  16 points

individual projects: 50 points (15points half-semester project, 35 points final project)

final exam: 34 points (24 points for compulsory written part, 10 points for optiona oral part)



The aim of the course is to review necessary linear algebra methods, make students familiar with classical machine learning as well as with deep learning and its most important individual methods, and to introduce the basic concepts of quantum computins as one of the possible future directions. The computer lab excercises help students to get practical experience with related algorithms and software tools.  

The graduate of the course will be able to (a) use basic machine learning methods for classification (b) use methods based on artificial neural networks (c) correctly choose a suitable machine learning method for the given task (d) discuss the use of machine learning methods in radio communications (e) discuss basic techniques of quantum computing and their use for given application

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Goodfellow, I., Bengio, Y., Courville, A., Deep Learning (Adaptive Computation and Machine Learning series), MIT Press, 2016, ISBN ‎ 0262035618 (EN)
Smola, A., Vishwanathan, S.V.N., Introduction to Machine Learning, Cambridge University press, available at (EN)
Mueller, J.P., Massaron, L. Machine Learning‎ For Dummies; 1st edition, 2016, ISBN : ‎ 1119245516 (EN)

Recommended reading

Not applicable.


Classification of course in study plans

  • Programme MPC-EKT Master's, 1. year of study, summer semester, compulsory-optional
  • Programme MPZ-EKT Master's, 1. year of study, summer semester, compulsory-optional
  • Programme MPA-TEC Master's, 1. year of study, summer semester, compulsory-optional
  • Programme MPAJ-TEC Master's, 1. year of study, summer semester, compulsory-optional

Type of course unit



26 hours, optionally

Teacher / Lecturer


1-Introduction to ML, course organization
2-Basics of linear algebra, Principal Component Analysis, PCA
3-Support Vector Machines (SVM)
4-K-means, KNN classification
5-Introduction to neural network (NN), linear/log regression
6-NN problems and tuning
7-Convolutional NN
8-Transfer learning
9-Recurrent NN, LSTM networks
10-Generative networks, GAN networks
11-Industrial talk – use of neural networks in manufacturing
12-Quantum information - basic arithmetic
13-Quantum information – quantum gates and circuits


Exercise in computer lab

26 hours, compulsory

Teacher / Lecturer


1-Introduction, algebra, Collab
5-Neural Network (NN) introduction
6-NN tuning, Miniproject assignment
8-Convolutional NN
9-Recurent NN, LSTM
12-Quantum arithmetic
13-Quantum circuits