| Lecture | Date | Topic | Lecturer | Pdf | Notes |
| 1. | 26. 9. | Introduction | BF | | |
| 2. | 3. 10. | Predictor evaluation | VF | , print: | [1] Chap 2, [2] Chap 7 |
| 3. | 10. 10. | Empirical risk minimization | VF | , print: | [1] Chap 2, [2] Chap 7 |
| 4. | 17. 10. | Probably Approximately Correct Learning | VF | , print: | [1] Chap 4, [2] Chap 12 |
| 5. | 24. 10. | Structured Output Support Vector Machines | VF | , print: | [1] Chap 5, [2] Chap 12 |
| 6. | 31. 10. | Supervised learning for deep networks | JD | | |
| 7. | 7. 11. | SGD, Deep (convolutional) networks | JD | | |
| 8. | 14. 11. | Generative learning, Maximum Likelihood estimator | BF | | L. Wasserman, Exp. Fam. |
| 9. | 21. 11. | EM algorithm, Bayesian learning | BF | | will be held in KN:A-320 |
| 10. | 28. 11. | Hidden Markov Models I | BF | | |
| 11. | 5. 12. | Hidden Markov Models II | BF | | |
| 12. | 12. 12. | Ensembling I | JD | | [4] |
| 13. | 19. 12. | Ensembling II | JD | | [2] Chap 10 |
| 14. | 9. 1. | Q&A | All | | |