Syllabus

Lecture Date Topic Lecturer Pdf Notes
1.20. 9. Introduction BF
2.27. 9. Predictor evaluation and learning via using empirical risk VF , to print: [1] Chap 2, [2] Chap 7
3.4. 10. Empirical risk minimization VF , to print: [1] Chap 2, [2] Chap 7
4.11. 10. Empirical risk minimization II VF , to print: [1] Chap 4, [2] Chap 12
5.18. 10. Structured Output Support Vector Machines VF , to print: [1] Chap 5, [2] Chap 12
6.25. 10. Supervised learning for deep networks JD
7.1. 11. SGD, Deep (convolutional) networks JD SGD Deep ANNs
8.8. 11. Generative learning, Maximum Likelihood estimator BF
9.15. 11. EM algorithm, Bayesian learning BF
10.22. 11. Hidden Markov Models I BF This lecture is held at Dejvice campus, room T2_C3-340
11.29. 11. Hidden Markov Models II BF
12.6. 12. Ensembling I JD [4]
13.13. 12. Ensembling II JD [2] Chap 10
14.10. 1. Q&A All