Theoretical Concepts of Machine Learning (1UE)
| Course no.: | 365.042 |
| Lecturers: | Gundula Povysil Andreas Mayr Thomas Unterthiner |
| Times/locations: | Mon 13:45-14:30, room S2 059 Start: Mon, March 3, 2014 |
| Mode: | UE, 1h, weekly |
| Registration: | KUSSS |
Motivation:
This practical course complements the lecture Theoretical Concepts of Machine Learning and aims at practicing the concepts and methods acquired in the lecture. Topics:- Generalization error
- Bias-variance decomposition
- Error models
- Model comparisons
- Estimation theory
- Statistical learning theory
- Worst-case and average bounds on the generalization error
- Structural risk minimization
- Bayes framework
- Evidence framework for hyperparameter optimization
- Optimization techniques
- Theory of kernel methods