Lecture | Date | Topic | Lecturer | Pdf | Notes |
1. | 2.10. | Introduction | BF | | |
2. | 9.10. | Empirical risk minimization I | VF | | chap 2 in [1] |
3. | 16.10. | Empirical risk minimization II | VF | | chap 3 in [1] |
4. | 23.10. | Support Vector Machines | VF | | chap 4, 5 in [1] |
5. | 30.10. | Supervised learning for deep networks | JD | | |
6. | 6.11. | Deep (convolutional) networks | JD | | |
7. | 13.11. | Unsupervised learning, EM algorithm, mixture models | BF | | |
8. | 20.11. | Bayesian learning | BF | | |
9. | 27.11. | Hidden Markov Models | BF | | |
10. | 4.12. | Structured output SVMs | VF | | |
11. | 11.12. | Markov Random Fields | BF | | |
12. | 18.12 | Ensembling I | JD | | |
13. | 8.1. | Ensembling II | JD | | |