Multi-valued Logic Applications (FSI-SAL)

Academic year 2025/2026
Supervisor: prof. RNDr. Miloslav Druckmüller, CSc.  
Supervising institute: ÚM all courses guaranted by this institute
Teaching language: Czech
Aims of the course unit:

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.
Learning outcomes and competences:
 
Prerequisites:
 
Course contents:
 
Teaching methods and criteria:
 
Assesment methods and criteria linked to learning outcomes:
 
Controlled participation in lessons:
 
Type of course unit:
    Lecture  13 × 2 hrs. compulsory                  
    Computer-assisted exercise  13 × 1 hrs. compulsory                  
Course curriculum:
    Lecture

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

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.
Literature - fundamental:
1.

KIM, Phil. MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence. Berkeley, CA: Apress, 2017. ISBN 978-1-4842-2845-6.
2. GURNEY, Kevin. An Introduction to Neural Networks. Florida, USA: CRC Press, 1997. ISBN 13 978-1857285031.
3.

Neural Networks and Deep Learning. Online. Michael Nielsen, 2015. Dostupné z: http://neuralnetworksanddeeplearning.com/. [cit. 2023-10-30].
4. Druckmüller, M.: Technické aplikace vícehodnotové logiky, PC- DIR , Brno 1998
Literature - recommended:
1. Neural Networks and Deep Learning. Online. Michael Nielsen, 2015. Dostupné z: http://neuralnetworksanddeeplearning.com/. [cit. 2023-10-30].
The study programmes with the given course:
Programme Study form Branch Spec. Final classification   Course-unit credits     Obligation     Level     Year     Semester  
N-MAI-P full-time study --- no specialisation -- GCr 4 Elective 2 1 S