===== Syllabus =====


^Week ^Date ^Topic ^Lecturer  ^Pdf ^Notes ^
|1.|24. 9.| **Introduction** | VF | {{ :courses:be4m33ssu:intro_ws2024.pdf | }} | |
|2.|1. 10.| **Supervised learning for deep networks** | JD | {{ :courses:be4m33ssu:anns_ws2024.pdf | }} | |
|3.|8. 10.| **Predictor evaluation** | VF | {{ :courses:be4m33ssu:pe_ws2024.pdf | }} (print {{ :courses:be4m33ssu:pe_ws2024_print.pdf | }})| [1] Chap 2, [2] Chap 7 | 
|4.|15. 10.| **Empirical risk minimization**  | VF | {{ :courses:be4m33ssu:erm_ws2025.pdf | }} (print {{ :courses:be4m33ssu:erm_ws2025_print.pdf | }})| [1] Chap 2, [2] Chap 7 |
|5.|22. 10.| **Probably Approximately Correct Learning** | VF | {{ :courses:be4m33ssu:pac_ws2024.pdf | }} (print {{ :courses:be4m33ssu:pac_ws2024_print.pdf | }}) | [1] Chap 4, [2] Chap 12 |
|6.|29. 10.| //dean's day// | | |  |
|7.|5. 11.| **SGD, Deep (convolutional) networks** | JD | {{ :courses:be4m33ssu:sgd_ws2024.pdf |SGD}} {{ :courses:be4m33ssu:deep_anns_ws2024.pdf |deep nets}} | |
|8.|12. 11.| **Support Vector Machines** | VF | {{ :courses:be4m33ssu:svm_ws2024.pdf | }} | |
|9.|19. 12.| **Ensembling I** | JD | {{ :courses:be4m33ssu:ensembling_ws2024.pdf | }} | [4],  lecture moved to KN:A-320|
|10.|26. 1.| **Ensembling II** | JD |  | [2] Chap 10 |
|11.|3. 12.| **Generative learning, Maximum Likelihood estimator** | VF | {{ :courses:be4m33ssu:gener_ws2024.pdf | }} | 2025-01-15 Errata: slide 14, error in cumulant of Bernoulli |
|12.|10. 12.| **EM algorithm, Bayesian learning** | VF | {{ :courses:be4m33ssu:em_bayesian_ws2024.pdf | }} | |
|13.|17. 12.| **Hidden Markov Models I**  | JD |{{ :courses:be4m33ssu:hmms_ws2024.pdf | }} | [5] Chap 17 |
|14.|7. 12.| **Hidden Markov Models II** | JD | | |