|
Lecturer(s)
|
-
Černík Petr, doc. Ing. Ph.D.
|
|
Course content
|
1. Introduction - the definition of machine learning, brief history, motivational examples 2. The relation of machine learning to other artificial intelligence paradigms (especially the symbolic paradigm) 3. Types of machine learning - supervised learning, unsupervised learning, reinforcement learning (differences, basic principles, examples) 4. Supervised learning - detailed explanation of the principle, training and working phase, tasks suitable for supervised learning 5. Supervised learning as a classification task - principle, examples 6. Parameter setting of a classifier in a simple task with one input 7. Libraries for machine learning - overview, basic usage of a selected library 8. Implementation of a simple classifier in a selected programming language (using libraries) 9. Neural networks - introduction, biological inspiration 10. Neural networks - activation function, perceptron, explanation of the basic workings of the one neuron network, relation to other machine learning models 11. Neural networks - generalization for more complicated tasks (overview), the success of neural network 12. Limits of machine learning in practical applications - responsibility for decisions of machine learning systems, algorithmic bias
|
|
Learning activities and teaching methods
|
- Contact hours
- 52 hours per semester
- Graduate study programme term essay (40-50)
- 40 hours per semester
- Preparation for an examination (30-60)
- 40 hours per semester
|
| prerequisite |
|---|
| Knowledge |
|---|
| orient themselves in basic math concepts at the high school level understand the principles of writing a simple computer program use modern information technologies effectively |
| Skills |
|---|
| load and save data in text format using Python understand a simple code in Python and, if necessary, modify it appropriately read a popular-science article in both Czech and English and prepare a presentation based on it |
| Competences |
|---|
| N/A |
| N/A |
| N/A |
| learning outcomes |
|---|
| Knowledge |
|---|
| understand the principle of machine learning explain the relation between machine learning and other paradigms of artificial intelligence characterize basic types of machine learning |
| Skills |
|---|
| use Python machine learning libraries on an elementary level analyze the suitability of machine learning methods for specific tasks describe the risks of using machine learning in practice |
| Competences |
|---|
| N/A |
| teaching methods |
|---|
| Knowledge |
|---|
| Lecture |
| Lecture with visual aids |
| Interactive lecture |
| Skills |
|---|
| Interactive lecture |
| Practicum |
| Task-based study method |
| Competences |
|---|
| Lecture with visual aids |
| Task-based study method |
| assessment methods |
|---|
| Knowledge |
|---|
| Combined exam |
| Seminar work |
| Skills |
|---|
| Combined exam |
| Seminar work |
| Competences |
|---|
| Combined exam |
| Seminar work |
|
Recommended literature
|
-
Aurélien Géron. Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems.
-
Oliver Theobald. Machine Learning For Absolute Beginners: A Plain English Introduction (Machine Learning From Scratch). 2018.
|