Lect. | Topic | Pdf |
01 | Markov chains, equivalent representations, ergodicity, convergence theorem for homogeneous Markov chains. | |
02 | Hidden Markov Models on chains for speech recognition: pre-processing, dynamic time warping, HMM-s. | |
03 | Inference tasks for Hidden Markov Models | |
04 | HMMs as exponential families, supervised learning: maximum likelihood estimator | |
05 | Supervised learning: Emprirical risk minimisation for HMMs | |
06 | Unsupervised learning: EM algorithm for HMMs | |
07 | Extensions of Markov models and HMMs: acyclic graphs, uncountable feature and state spaces | |
08 | Extensions of Markov models and HMMs: acyclic graphs, uncountable feature and state spaces (cont'd) | |
09 | Markov Random Fields - Markov models on general graphs. Equivalence to Gibbs models | |
10 | Searching the most probable state configuration: transforming the task into a MinCut-problem for the submodular case. | |
11 | Searching the most probable state configuration: approximation algorithms for the general case. | |
12 | Searching the most probable state configuration: approximation algorithms for the general case. (cont'd) | |
13 | The partition function and marginal probabilities: approximation algorithms for their estimation. | |
14 | Parameter learning for Gibbs random fields | |