| Course title | Artificial and Computational Intelligence |
|---|---|
| Course code | FES/EUVIA |
| Organizational form of instruction | Lecture + Seminar |
| Level of course | Doctoral |
| Year of study | not specified |
| Semester | Winter and summer |
| Number of ECTS credits | 10 |
| Language of instruction | English |
| Status of course | Compulsory-optional |
| Form of instruction | Face-to-face |
| Work placements | This is not an internship |
| Recommended optional programme components | None |
| Lecturer(s) |
|---|
|
| Course content |
|
Generalization of fuzzy sets. Approaches to generalizing fuzzy inference systems and their learning capabilities. Advances in learning theory. Extreme learning machines. Contemporary approaches to meta-learning. Deep learning in neural networks. Convolutional neural networks. Regularization of neural networks. Neuro-fuzzy-genetic systems. Optimization using swarm intelligence - particle swarm, ant and artificial bee colonies, bat algorithm, etc. Contemporary artificial and computational intelligence approaches to big data analysis.
|
| Learning activities and teaching methods |
| unspecified |
| Learning outcomes |
|
The aim of the course is to acquaint students with the current state of knowledge in the field of artificial and computational intelligence, including its emerging theories, methods, and research challenges at the intersection of the subject.
|
| Prerequisites |
|
unspecified
|
| Assessment methods and criteria |
|
unspecified
Completion and successful defense of a project based on the covered material, focusing on a written paper for the state doctoral exam and the doctoral dissertation. Examination: oral, with a minimum pass rate of 60%. |
| Recommended literature |
|
| Study plans that include the course |
| Faculty | Study plan (Version) | Category of Branch/Specialization | Recommended semester |
|---|