Course detail

Artificial Intelligence

FEKT-BPC-UINAcad. year: 2026/2027

The course provides a systematic introduction to the field of artificial intelligence, covering a broad spectrum from classical symbolic methods through evolutionary algorithms to modern neural networks. Students will gain an overview of the fundamental principles of AI and will learn to work with state space search, game-playing algorithms, fuzzy logic, and bio-inspired approaches.

The second half of the course focuses on artificial neural networks (ANNs), which today represent a major direction in AI development. The curriculum covers everything from foundational models (perceptron, ADALINE), through topologically organized networks (SOM, RBF), to deep neural networks, convolutional and recurrent architectures, autoencoders, generative models, and large language models. The course enables students to understand how neural networks function, their areas of application, and their inherent limitations.

Graduates of the course will acquire a comprehensive and up-to-date overview of the tools, principles, and trends in artificial intelligence, as well as the ability to navigate the rapidly evolving AI landscape.

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Guarantor

prof. Ing. Radomil Matoušek, Ph.D.

Department

Department of Control and Instrumentation (UAMT)

Entry knowledge

A basic knowledge of linear algebra, algorithm design, and statistics is required.

Rules for evaluation and completion of the course

To be awarded credit for the course, all of the following conditions must be met:

  • 100% attendance in the mandatory parts of instruction. Attendance at computer lab sessions is compulsory; a missed session can be made up upon agreement with the instructor, provided a valid excuse is given.

  • Completion of two online training courses, each confirmed by a certificate.

  • Submission of three projects, each worth a minimum of 5 points and a maximum of 10 points. Each project must be submitted and defended within the assigned timeframe. The maximum number of points achievable from the projects is 30, which is added to the final exam score.

The final exam consists of a written and oral part, with a maximum of 70 points. A score below 35 points results in failing the exam. The final grade is based on the sum of points from the exam and the exercises.

Aims

The aim of the course is to introduce students to selected methods and approaches in artificial intelligence (AI), covering both classical symbolic AI (GOFAI) and modern subsymbolic AI, with particular emphasis on neural networks. The objective of the course is thus to clarify the theoretical foundations of the discussed AI methods, to understand their implementation and application possibilities, and to develop the ability to critically evaluate the suitability of their use in practice.

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

MAŘÍK, Vladimír, ŠTĚPÁNKOVÁ, Olga, LAŽANSKÝ, Jiří a kolektiv. Umělá inteligence (1. až 6. díl) Praha: Academia 1993 - 2013. (CS)
RUSSELL, Stuart a NORVIG, Peter. Artificial Intelligence. A Modern Aproach. New Jersey: Pearson 2021. 1170 s. ISBN-13: 978-1-292-40113-3 (EN)

Recommended reading

DUDA, Richard, HART Peter a STORK David. Pattern Classification. New York: John Wiley & Sons, INC. 2001. 654 s. ISBN 0-471-05669-3. (EN)
SONKA, Milan, HLAVAC, Vaclav a BOYLE, Rogert. Image Processing, Analysis and Machine Vision. Toronto: Thomson, 2008. 829 s. ISBN 978-0-495-24438-7. (EN)

Classification of course in study plans

  • Programme BPC-TLI Bachelor's 0 year of study, winter semester, elective
  • Programme BPC-SEE Bachelor's 0 year of study, winter semester, elective
  • Programme BPC-NCP Bachelor's 0 year of study, winter semester, elective
  • Programme BPC-MET Bachelor's 0 year of study, winter semester, elective
  • Programme BPC-IBE Bachelor's 0 year of study, winter semester, elective
  • Programme BPC-EMU Bachelor's 3 year of study, winter semester, compulsory-optional
  • Programme BPC-ECT Bachelor's 0 year of study, winter semester, elective

  • Programme BPC-AUD Bachelor's

    specialization AUDB-ZVUK , 0 year of study, winter semester, elective
    specialization AUDB-TECH , 0 year of study, winter semester, elective

  • Programme BPC-AMT Bachelor's 3 year of study, winter semester, compulsory

Type of course unit

 

Lecture

26 hod., compulsory

Teacher / Lecturer

prof. Ing. Radomil Matoušek, Ph.D.

Syllabus

  • Artificial Intelligence (AI). Taxonomy, philosophy, law, future.
  • State Space and Uninformed Search.
  • State Space and Informed Search. [Project 1 info]
  • Game Playing Methods. Minimax algorithm. Alpha-beta pruning.
  • Expert Systems (called expert - doc. Jirsík).
  • Bio-Inspired Algorithms (GA, DE, PSO, and SWARM).
  • Advanced Metaheuristics. Surrogate Models. [Project 2 info]
  • Artificial Neural Networks (ANN) - Paradigms, Perceptron, ADALINE.
  • Topologically Organized ANN (SOM, Kohonen) and RBF Networks - Paradigms.
  • Deep Neural Networks (DNN) - Paradigms, MLP, RBM, Backpropagation, etc., Autoencoders and their applications.
  • Convolutional Neural Networks (CNN). Multi-classification. [Project 3 info]
  • Recurrent Neural Networks (RNN, LSTM, GRU), Encoder-decoder Architectures.
  • Generative Neural Network Models. LLM. Transformers.
  • Colloquium for the course and a selected topic (e.g., SNN, GNN, Physics-Informed Neural Networks, or Bayesian Networks).

Exercise in computer lab

26 hod., compulsory

Teacher / Lecturer

prof. Ing. Radomil Matoušek, Ph.D.

Syllabus

  1. Lab: Python Basics, MATLAB Capabilities (Programming Basics).
  2. Lab: A in a Simple Maze vs. BFS/DFS/A*.
  3. Lab: 8-puzzle. [Project 1]
  4. Lab: [Project 1 – defense]
  5. Lab: GA, DE, PSO: Global Optimization (Benchmarking, Controller Design). [Project 2]
  6. Lab: GA, HC12: Combinatorial Optimization (TSP).
  7. Lab: [Project 2 – defense]
  8. Lab: Linear Classifier, Perceptron, XOR and EA Learning.
  9. Lab: Simple Clustering (SOM).
  10. Lab: Data Approximation (Regression). [Project 3]
  11. Lab: (Keras/PyTorch) Classification 1/2 (MNIST).
  12. Lab: (Keras/PyTorch) Classification 2/2 (ImageNet).
  13. Lab: [Project 3 – defense].