|
Lecturer(s)
|
-
Psutka Josef, doc. Ing. Mgr. Ph.D.
|
|
Course content
|
Introduction to machine recognition of objects and phenomena, basics of learning systems. Course outline: Bayesian decision theory - Bayes Theorem, MAP, minimum loss criterion, probabilistic discriminant function, linear discriminant function classifier, minimum distance classifier, nearest neighbor classifier, k-nearest neighbors, regression - univariate linear regression, multivariate linear regression, logistic regression, non-hierarchical clustering methods - k-means algorithm, iterative optimization, hierarchical clustering methods - agglomerative methods, division methods, binary division, neural networks - introduction, mathematical models of perceptron, MLP, back propagation algorithm, SGD, BGD, optimization of training, regularization, underfitting, overfitting, deep neural networks - CNN, RNN
|
|
Learning activities and teaching methods
|
Lecture supplemented with a discussion, One-to-One tutorial, Practicum
- Contact hours
- 26 hours per semester
- Practical training (number of hours)
- 39 hours per semester
- Individual project (40)
- 40 hours per semester
- Presentation preparation (report) (1-10)
- 10 hours per semester
- Preparation for an examination (30-60)
- 45 hours per semester
|
| prerequisite |
|---|
| Knowledge |
|---|
| have basic skills in mathematical analysis and linear algebra |
| have basic skills in the theory of probability and statistics |
| Skills |
|---|
| apply the basics of mathematical analysis and linear algebra when solving specific tasks |
| apply the basics of probability theory and statistics when solving specific tasks |
| ability to write algorithms for given theoretical problems |
| Competences |
|---|
| N/A |
| learning outcomes |
|---|
| Knowledge |
|---|
| define the basic tasks of machine learning (classification, regression) |
| understanding of basic machine learning techniques |
| characterize the differences between individual types of classifiers (Bayesian, linear, by minimum distance, by k-nearest neighbor) |
| grasp the fundamentals of neural networks |
| Skills |
|---|
| analyze basic types of classification tasks and choose a suitable type of classifier |
| implement classifiers with a general discriminant function (Bayesian classifier) |
| implement classifiers with a linear discriminant function |
| apply methods of cluster analysis |
| training a simple neural network |
| Competences |
|---|
| N/A |
| teaching methods |
|---|
| Knowledge |
|---|
| Lecture supplemented with a discussion |
| One-to-One tutorial |
| Skills |
|---|
| Lecture with visual aids |
| Competences |
|---|
| Individual study |
| assessment methods |
|---|
| Knowledge |
|---|
| Combined exam |
| Skills |
|---|
| Seminar work |
| Combined exam |
| Competences |
|---|
| Seminar work |
| Combined exam |
|
Recommended literature
|
-
Duda R.O., Hart P., Stork D.G. Pattern Classification Second Edition. A Wiley-Interscience Publication. 2000.
-
Kotek, Zdeněk, Mařík, Vladimír. Metody rozpoznávání a jejich aplikace. Academia, Praha, 1993. ISBN 80-200-0297-9.
-
Murphy K.P. Probabilistic Machine Learning. The MIT Press. 2022.
-
Theodoridis S., Koutroumbas K. Pattern Recognition Third Edition. Academic Press. 2006.
|