===== Syllabus =====


^Lecture ^Date ^Topic ^Lecturer  ^Pdf ^Notes ^
|1.|21. 9.| **Introduction** | BF | {{:courses:be4m33ssu:stat_mach_learn_l01.pdf| }}  | |
|2.|28. 9.| — National holiday — |  |  |  |
|3.|5. 10.| **Empirical risk** | VF | {{ :courses:be4m33ssu:er_ws2021.pdf | }} (to print {{ :courses:be4m33ssu:er_print_ws2021.pdf | }}) | [1] Chap 2, [2] Chap 7 |
|4.|12. 10.| **Empirical risk minimization**  | VF | {{ :courses:be4m33ssu:erm_ws2021.pdf | }} (to print {{ :courses:be4m33ssu:erm_print_ws2021.pdf | }})| [1] Chap 2, [2] Chap 7 | 
|5.|19. 10.| **Empirical risk minimization II** | VF | {{ :courses:be4m33ssu:erm2_ws2021.pdf | }} (to print {{ :courses:be4m33ssu:erm2_print_ws2021.pdf | }}) | [1] Chap 4, [2] Chap 12 |
|6.|26. 10.| **Structured Output Support Vector Machines** | VF | {{ :courses:be4m33ssu:sosvm_ws2021.pdf | }} (to print {{ :courses:be4m33ssu:sosvm_print_ws2021.pdf | }})| [1] Chap 5, [2] Chap 12 |
|7.|2. 11.| **Supervised learning for deep networks** | JD | {{ :courses:be4m33ssu:anns_ws2021.pdf | }} | |
|8.|9. 11.| **SGD, Deep (convolutional) networks** | JD | {{ :courses:be4m33ssu:sgd_ws2021.pdf |SGD}} {{ :courses:be4m33ssu:deep_anns_ws2021.pdf | Deep networks}} | |
|9.|16. 11.| **Generative learning, Maximum Likelihood estimator** | BF | {{ :courses:be4m33ssu:ml-em.pdf | }} | |
|10.|23. 11.| **EM algorithm, Bayesian learning** | BF | {{ :courses:be4m33ssu:em_bayesian-ws2021.pdf | }} | takes place in KN:A-214 |
|11.|30. 11.| **Hidden Markov Models**  | BF | {{ :courses:be4m33ssu:hmms.pdf | }} | |
|12.|7. 12.| **Markov Random Fields** | BF | {{ :courses:be4m33ssu:mrfs.pdf | }}| Contents of this lecture are not examined |
|13.|14. 12.| **Ensembling I** | JD | {{ :courses:be4m33ssu:ensembling_ws2021.pdf | }} | [4] |
|14.|4. 1.| **Ensembling II** | JD |  | [2] Chap 10 |