====== Lectures ======
  * Tuesdays, 12:45-14:15, KN:E-301
  * Lecturers: Petr Pošík (PP), Radek Mařík (RM)

List of {{:courses:ui:ui-competencies.pdf|competencies}} you should have after individual lectures. (Will be updated continuously.)

<WRAP round todo>
The order of lectures is subject to change. \\
The PDFs are from previous years. They will be updated during the semester.
</WRAP>

===== Regular lectures =====

^ Date ^ W# ^ Who ^ Contents ^ Materials ^
| 18.02. |   1 | PP | AI, PR, learning and robotics. Decision tasks. Empirical learning. | {{ :courses:ui:b01bayes-slides.pdf |Slides}}. {{ :courses:ui:b01bayes-handouts.pdf |Handouts}}. (Upd. 2020-02-26) |
| 25.02. |   2 | PP | Linear methods for classification and regression. | {{:courses:ui:b02linear-slides.pdf|Slides}}. {{:courses:ui:b02linear-handouts.pdf|Handouts}}. (Upd. 2020-03-03) |
| 03.03. |   3 | PP | Non-linear models. Feature space straightening. Overfitting. | {{:courses:ui:b03overfitting-slides.pdf|Slides}}. {{:courses:ui:b03overfitting-handouts.pdf|Handouts}}. (Upd. 2020-03-03) |

/* | 10.03. |   4 | RM | Nearest neighbors. Kernel functions, SVM. Decision trees. | {{:courses:ui:b04nonlinear-slides.pdf|Slides}}. {{:courses:ui:b04nonlinear-handouts.pdf|Handouts}}. (Upd. 2020-03-17) [[:courses:ui:selfstudy:start#lecture_4|Self-study]] |
| 17.03. |   5 | PP | Bagging. Adaboost. Random forests. | {{:courses:ui:b05committees-slides.pdf|Slides}}. {{:courses:ui:b05committees-handouts.pdf|Handouts}}. (Upd. 2020-03-17)|
| 24.03. |   6 | PP | Neural networks. Basic models and methods, error backpropagation. | {{:courses:ui:b12nn-slides.pdf|Slides}}. {{:courses:ui:b12nn-handouts.pdf|Handouts}}. | 
| 31.03. |   7 | PP | Deep learning. Convolutional and recurrent NNs. | {{:courses:ui:b13deep-slides.pdf|Slides}}. {{:courses:ui:b13deep-handouts.pdf|Handouts}}. |              
| 07.04. |   8 | PP | Probabilistic graphical models. Bayesian networks. | {{:courses:ui:b06bayesnets-slides.pdf|Slides}}. {{:courses:ui:b06bayesnets-handouts.pdf|Handouts}}. |
| 14.04. |   9 | PP | Hidden Markov models. | {{:courses:ui:b07hmm-slides.pdf|Slides}}. {{:courses:ui:b07hmm-handouts.pdf|Handouts}}. |                                         
| 21.04. |  10 | PP | Expectation-Maximization algorithm. | {{:courses:ui:b08em-slides.pdf|Slides}}. {{:courses:ui:b08em-handouts.pdf|Handouts}}. |                             
| 28.04. |  11 | RM | Planning. Planning problem representations. Planning methods. | {{:courses:ui:p09.aiplanning.pdf|Handouts}}|
| 05.05. |  12 |    | **No lecture. Schedule as on wednesday.** |  | 
| 12.05. |  13 | RM | Constraint satisfaction problems. | {{:courses:ui:p11.constraintsatisfactionhandouts.pdf|Handouts}}  |
| 19.05. |  14 | RM | Scheduling. Local search. | {{:courses:ui:p10.schedulinghandouts.pdf|Handouts}} | 
*/

===== Lectures suspended =====
From March 10 to at least March 22, the teaching is suspended due to [[http://www.fel.cvut.cz/cz/covid/|coronavirus disease]].

===== Online lectures =====
Starting from March 23, the following lectures will be given online via BigBlueButton feature in BRUTE. The lectures will be held in the standard time, Tuesdays 12:45-14:15. Students will find a link to the video conference in BRUTE several minutes before the lecture starts, and they will receive an email with the invitation to join the lecture.


^ Date ^ W# ^ Who ^ Contents ^ Materials ^
| <del>10.03.</del> 24.3. |   4 | RM | Nearest neighbors. Kernel functions, SVM. Decision trees. | {{:courses:ui:b04nonlinear-slides.pdf|Slides}}. {{:courses:ui:b04nonlinear-handouts.pdf|Handouts}}. (Upd. 2020-03-17) [[:courses:ui:selfstudy:start#lecture_4|Self-study]] |
| <del>17.03.</del> 31.3. |   5 | PP | Bagging. Adaboost. Random forests. | {{:courses:ui:b05committees-slides.pdf|Slides}}. {{:courses:ui:b05committees-handouts.pdf|Handouts}}. (Upd. 2020-03-31) [[:courses:ui:selfstudy:start#lecture_5|Self-study]] |
| <del>24.03.</del> 7.4.|   6 | PP | Neural networks. Basic models and methods, error backpropagation. | {{:courses:ui:b12nn-slides.pdf|Slides}}. {{:courses:ui:b12nn-handouts.pdf|Handouts}}. (Upd. 2020-05-01) | 
| <del>31.03.</del> 14.4.|   7 | PP | Deep learning. Convolutional and recurrent NNs. | {{:courses:ui:b13deep-slides.pdf|Slides}}. {{:courses:ui:b13deep-handouts.pdf|Handouts}}. (Upd. 2020-04-14) |              
| <del>07.04.</del> 21.4. |   8 | PP | Probabilistic graphical models. Bayesian networks. | {{:courses:ui:b06bayesnets-slides.pdf|Slides}}. {{:courses:ui:b06bayesnets-handouts.pdf|Handouts}}. (Upd. 2020-04-20) |
| <del>14.04.</del> 28.4. |   9 | PP | Hidden Markov models. | {{:courses:ui:b07hmm-slides.pdf|Slides}}. {{:courses:ui:b07hmm-handouts.pdf|Handouts}}. (Upd. 2020-05-02) |                                         
| <del>21.04.</del> 5.5. |  10 |    | **No lecture. Schedule as on Friday.** |  |                              
| <del>28.04.</del> 12.5. |  11 | PP | Expectation-Maximization algorithm. | {{:courses:ui:b08em-slides.pdf|Slides}}. {{:courses:ui:b08em-handouts.pdf|Handouts}}. (Upd. 2020-05-15) | 
| <del>05.05.</del> 19.5. |  12 | RM | Planning. Planning problem representations. Planning methods. | {{:courses:ui:p09.aiplanning.pdf|Handouts}}|
| <del>12.05.</del> 26.5. |  13 | RM | Constraint satisfaction problems. | {{:courses:ui:p11.constraintsatisfactionhandouts.pdf|Handouts}}  |
| <del>19.05.</del> 2.6. |  14 | RM | Scheduling. Local search. | {{:courses:ui:p10.schedulinghandouts.pdf|Handouts}} | 




/*
  - The relation of artificial intelligence, pattern recognition, learning and robotics. Decision tasks, Empirical learning.
  - Linear methods for classification and regression.
  - Non-linear models. Feature space straightening. Overfitting.
  - Nearest neighbors. Kernel functions, SVM. Decision trees.
  - Bagging. Adaboost. Random forests.
  - * Graphical models. Bayesian networks.
  - * Markov statistical models. Markov chains.
  - * Expectation-Maximization algorithm.
  - Planning. Planning problem representations. Planning methods.
  - Scheduling. Local search.
  - Constraint satisfaction problems.
  - Neural networks. Basic models and methods, error backpropagation.
  - * Special neural networks. Deep learning.
  - Evolutionary algorithms (if time permits).
*/