SubjectsSubjects(version: 954)
Course, academic year 2021/2022
Computational Intelligence - P445004
Title: Počítačová inteligence
Guaranteed by: Department of Mathematics, Informatics and Cybernetics (446)
Faculty: Faculty of Chemical Engineering
Actual: from 2021 to 2022
Semester: both
Points: 0
E-Credits: 0
Examination process:
Hours per week, examination: 3/0, other [HT]
Capacity: winter:unknown / unknown (unknown)
summer:unknown / unknown (unknown)
Min. number of students: unlimited
State of the course: taught
Language: Czech
Teaching methods: full-time
Teaching methods: full-time
Additional information:
Note: course is intended for doctoral students only
can be fulfilled in the future
you can enroll for the course in winter and in summer semester
Guarantor: Švihlík Jan doc. Ing. Ph.D.
Is interchangeable with: AP445004
Annotation -
The subject is devoted to selected problems of computational intelligence and machine learning including architecture of artificial neural networks, their optimization for signal and image processing and their use for adaptive noise rejection. A special attention is paid to signal and image features extraction, pattern recognition and to the use of neural networks for their classification into given number of classes. Selected case studies presented in the MATLAB computational environment are devoted to biomedical and engineering data processing.
Last update: Kubová Petra (12.04.2018)
Aim of the course -

Students will know how

(i) to model multilayer and reccurent neural networks,

(ii) to create pattern matrices forming inputs for neural networks,

(iii) to optimize neural networks for data classification,

(iv) to use neural networks for noise cancelling and signal prediction

(v) to propose computationa environment for real data segmmentation and classification

Last update: Kubová Petra (12.04.2018)
Descriptors -

Computational intelligence, artificial neural networks, machine learning, pattern recognition

Last update: Kubová Petra (12.04.2018)
Literature -

Z: S. Haykin: Neural Networks, Prentice Hall, 1999, ISBN 0132733501

Z: S. Samarasinghe: Neural Networks for Applied Science and Engineering, CRC Press, 2016

D: Vaseghi S.V.: Multimedia Signal Processing, Wiley, 2007

D: WIKIBOOK: Artificial Neural Networks,, 2018

Last update: Kubová Petra (12.04.2018)
Learning resources -

Last update: Kubová Petra (12.04.2018)
Teaching methods -

Lectures and practical verification of proposed algorithms in the computer laboratory.

Last update: Kubová Petra (12.04.2018)
Requirements to the exam -

During studies of this subject it is necessary either to submit the own paper using computational intelligence in the area of own research or to evaluate three projects and their solution in MATLAB.

Last update: Kubová Petra (12.04.2018)
Syllabus -

1. Computational intelligence in data processing

2. Architecture of artificial neural networks, their modelling and optimization in the MATLAB environment

3. Learning and verification

4. Adaptive lineare element and their use in signal denoising

5. Multilayesr feedforward and recurrent neural networks in signal prediction

6. Feature matrix construction and classification methods in signal and image processing

7. Neural networks with topology, alternative methods of data classification

8. Machine learning, pattern recognition

9. Neural networks in image processing

10. Neural networks based on deep learning

11. Selected applications of adaptive signal processing, neural networks in robotics

12: CASE STUDY 1: Real data denoising

13. CASE STUDY 2: Signal prediction

14. CASE STUDY 3: Feature extraction and classification in biomedicine

Last update: Kubová Petra (12.04.2018)
Entry requirements -


Last update: Soušková Hana (12.06.2018)
Registration requirements -


Last update: Soušková Hana (12.06.2018)
Course completion requirements -

Participation on the final colloquium with the presentation and discussion of a selected research topic.

Last update: Kubová Petra (12.04.2018)