450-4049/04 – Applied Artificial Intelligence Methods (AUI)
| Gurantor department | Department of Cybernetics and Biomedical Engineering | Credits | 4 |
| Subject guarantor | prof. Ing. Martin Černý, Ph.D. | Subject version guarantor | prof. Ing. Martin Černý, Ph.D. |
| Study level | undergraduate or graduate | | |
| | Study language | English |
| Year of introduction | 2019/2020 | Year of cancellation | |
| Intended for the faculties | FEI | Intended for study types | Follow-up Master |
Subject aims expressed by acquired skills and competences
Students will learn about the basics of the science of artificial intelligence, learn about its tools in engineering application areas with respect to the teaching of the subject in the given study program. They will learn about the methods of synthesis of simple artificial intelligence systems. Students will be able to make practical use of artificial intelligence tools, design a fuzzy expert system, an artificial neural network or an optimization algorithm with respect to applications in their field of study.
Teaching methods
Lectures
Tutorials
Experimental work in labs
Summary
The course is primarily focused on gaining knowledge of the function and potential application of artificial intelligence methods in the context of their programme of study. The course will introduce students to selected artificial intelligence methods and focus on their practical implementation in their engineering practice. Core areas include fuzzy logic and expert systems, cluster analysis and optimization methods, neural networks, decision trees and forests, machine learning methods without neural networks, hybrid and special machine learning methods, and the use of generative artificial intelligence.
Compulsory literature:
Recommended literature:
Additional study materials
Way of continuous check of knowledge in the course of semester
Ongoing monitoring of studies:
Continuous monitoring is carried out on the basis of the student's participation in laboratory exercises.
Conditions for awarding classified credit:
The student may achieve 60 points for the completion of the tasks in the practical computer exercises. The minimum number of points to be awarded is 20.
To pass the course, the student must pass a written test focused on theoretical knowledge with a minimum score of 20 out of 40 possible points.
E-learning
Materials are available at https://lms.vsb.cz/?lang=en.
Consultation through MS Teams.
Other requirements
There are not defined other requirements for students
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
Lectures
1. Principles and methods of artificial intelligence. Methods of computer knowledge representation and language modelling. Basics of fuzzy mathematics and fuzzy logic
2. Fuzzy expert systems
3. Fuzzy models and ANFIS
4. Data classification: basic methods, principles and applications Hierarchical and non-hierarchical cluster analysis methods.
5. and 6. Neural networks: basic principles, topologies, network types and applications for classification and prediction.
7. Optimization methods and applications.
8. Decision trees and forests, random trees.
9. a 10. Machine learning methods without neural networks
11. Special machine learning methods: reinforcement learning, federated learning, transfer learning, multi-source and multi-view learning
12. Hybrid methods
13. Generative artificial intelligence and its application in engineering practice.
Computer exercises
1. Mathematical applications of fuzzy mathematics.
2. Design and implementation of fuzzy expert systems.
3. Application of fuzzy modeling on real examples.
4. Implementation of selected classification algorithms in the context of engineering applications.
5. Design and implementation of neural networks in MATLAB environment for solving classification and prediction tasks.
6. Application of optimization techniques.
7. Implementation of cluster analysis methods for biomedical data segmentation and classification.
8. Implementation of decision tree methods
9. Implementation of machine learning methods without neural networks
10. implementation of selected special machine learning methods in engineering applications
11. Implementation of selected hybrid methods in engineering applications
12. Experimentation with generative artificial intelligence
13. Credit test
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction