Lecture | Date | Topic | Lecturer | Pdf | Notes |
1. | 24. 9. | Introduction | BF | | |
2. | 1. 10. | Empirical risk | VF | , ( printable: ) | ch 2 in [1] |
3. | 8. 10. | Empirical risk minimization | VF | , ( printable: ) | ch 2 in [1], ch 3 in [1] |
4. | 15. 10. | Support Vector Machines I | VF | , ( printable: ) | ch 4 in [1], ch 12 in [2] |
5. | 22. 10. | Support Vector Machines II | VF | , (printable: ) | ch 5 in [1] |
6. | 29. 10. | Supervised learning for deep networks | JD | | |
7. | 5. 11. | Deep (convolutional) networks | JD | , SGD | |
8. | 12. 11. | Unsupervised learning, EM algorithm, mixture models | BF | | |
9. | 19. 11. | Bayesian learning | BF | | |
10. | 26. 11. | Hidden Markov Models | BF | | |
11. | 3. 12. | Markov Random Fields | BF | | for additional reading (not part of the exam) |
12. | 10. 12. | Ensembling I | JD | | |
13. | 17. 12. | Ensembling II | JD | | |
14. | 7. 1. | reserve | | | |