Course detail

Multi-valued Logic Applications

FSI-SALAcad. year: 2025/2026

The course is devoted to artificial intelligence algorithms in both theoretical and practical aspects. In the course, students will learn about the theoretical mathematical background of each area of methods and then implement them. Matlab is used as the programming environment and some implementations will be presented in Python.

The first part of the course covers machine learning methods - kNN, Support Vector Machine, decision trees. The second part discusses various neural networks, deep learning and more complex R-CNNs and autoencoders. Students will learn how to create their own training and test data, build appropriate layers such as convolutional neural networks, perform validation and evaluation of results.

The course also includes invited lectures on language analysis using neural networks.

Language of instruction

Czech

Number of ECTS credits

4

Mode of study

Not applicable.

Guarantor

prof. RNDr. Miloslav Druckmüller, CSc.

Department

Institute of Mathematics (ÚM)

Entry knowledge

Programming skills in Matlab, statistical methods.

Rules for evaluation and completion of the course

Graded assessment based on submission of semester work (70 percent) and oral exam of the given theory (30 percent).


Participation on lessons is compulsory, in case of absence it is necessary to work out substitute work.

Aims

The aim of the course is to introduce students to the mathematical background of artificial intelligence methods and also to teach them how to implement these methods with understanding.

The areas that will be covered in the course, which students will study and program:

1. Nearest Neighbor Method, Decision Trees, Support Vector Machine.

2. Building a neural network for training on tabular data.

3. Convolutional neural networks for working with image data.

4. R-CNN for detecting a particular object in images.

5. Autoencoders and decoders.

Study aids

Materials and lecture notes on e-learning.

Prerequisites and corequisites

Not applicable.

Basic literature

Druckmüller, M.: Technické aplikace vícehodnotové logiky, PC- DIR , Brno 1998 (CS)
GURNEY, Kevin. An Introduction to Neural Networks. Florida, USA: CRC Press, 1997. ISBN 13 978-1857285031. (EN)
Neural Networks and Deep Learning. Online. Michael Nielsen, 2015. Dostupné z: http://neuralnetworksanddeeplearning.com/. [cit. 2023-10-30]. (EN)
KIM, Phil. MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence. Berkeley, CA: Apress, 2017. ISBN 978-1-4842-2845-6. (EN)

Recommended reading

Neural Networks and Deep Learning. Online. Michael Nielsen, 2015. Dostupné z: http://neuralnetworksanddeeplearning.com/. [cit. 2023-10-30]. (EN)

Classification of course in study plans

  • Programme N-MAI-P Master's 1 year of study, summer semester, elective

Type of course unit

 

Lecture

26 hod., compulsory

Teacher / Lecturer

prof. RNDr. Miloslav Druckmüller, CSc.

Syllabus

1. Relationship of artificial intelligence methods to expert systems.

2.-3. Machine learning methods (kNN, decision trees, SVM, etc.).

4.-5. Basic neural network design for tabular data, explanation of back-propagation.

6.- 7. Convolutional neural networks (convolution, pooling, batch normalization).

8. Autoencoders and decoders.

9. Pre-trained CNN - implementation, properties

10. R-CNN (convolutional neural network for image retrieval), transformers.

11.-12. Work on semester projects and tutorials.

13. Presentation of final projects and evaluation.

Computer-assisted exercise

13 hod., compulsory

Teacher / Lecturer

prof. RNDr. Miloslav Druckmüller, CSc.

Syllabus

Lectures are in Matlab or Python using libraries: scikit-learn, pandas, keras, pytorch.

1. Design of expert system in Matlab (connection with fuzzy logic).

2.-3. Implementation of kNN, decision trees, and SVM methods on different data. Test and validation data.

4.-5. Design of neural networks for prediction on given data (e.g., medical data, economic indicators, etc.).

6.-7. Processing of image databases for designing convolutional neural networks (recognition of handwritten digits, geometric shapes, animals).

8. Autoencoders and decoders - implementation for noise reduction, image retrieval, and data dimensionality reduction.

9. Pre-trained CNN - ResNet, GoogleNet

10. R-CNN, YOLO on real data.

11.-12. Semester project consultation.

13. Presentation and evaluation of work.