1. Training
1.1. cross validation
1.1.1. n-fold cross validation
2. Preprocessing
2.1. Feature Transform
2.2. Normalization
2.3. Regularization
3. Postulates
3.1. Represantive Sample Set
3.2. Features
3.3. Compactness
3.4. Similarity
3.5. Decomposition
3.6. Structure
4. Classification
4.1. supervised
4.2. unsupervised
4.3. Evaluation
4.3.1. Accuracy Rate
4.3.2. Recall&Precision (f-measure)
4.3.3. Average Call
4.3.4. ROC curve
4.3.5. Estimating Classifiers
4.3.5.1. Crossvalidation
4.3.5.2. Jackknife
4.3.5.3. Bootstrap
4.3.5.4. m-fold
4.4. Boosting
4.4.1. Adaboost
4.5. loss functions
4.5.1. 0/1-loss
4.5.2. least squares
4.5.3. hinge loss
4.5.4. exponential
4.5.5. average loss
4.6. Classifiers
4.6.1. Statistical
4.6.1.1. Mixture Densities
4.6.1.2. Bayesian
4.6.1.2.1. Naive Bayes
4.6.1.2.2. Gaussian
4.6.2. Parametric
4.6.2.1. Linear Regression
4.6.2.1.1. Rosenblatt Perceptron
4.6.2.2. Logistic Regression
4.6.2.3. Support Vector Machines
4.6.2.3.1. Kernels
4.6.3. Non-Parametric
4.6.3.1. Estimation
4.6.3.2. Nearest Neighbor
4.6.3.3. k-Nearest Neighbor
4.6.3.4. Multilayer Perceptrons
4.6.3.4.1. Aktivierungsfunktionen
4.7. Hilfsfunktionen
4.7.1. Log-Likelihood
4.7.2. Lagrange-Multiplier
4.7.2.1. KKT conditions
4.7.2.2. slaters condition
4.7.3. Dynamic Time Warping
4.7.4. Kullback-Leibler
4.7.5. Parameter-Estimation Methods
4.7.5.1. Maximum a-posteriori Estimation
4.7.5.2. EM Algorithmus
4.7.5.3. MAP
4.7.5.4. ML Estimation
4.7.5.5. Maximum Likelihood
4.8. Discriminant Analysis Methods
4.8.1. discriminative
4.8.1.1. Logistic Regression
4.8.1.2. Support Vector Machines
4.8.1.3. k-Nearest Neighbor
4.8.1.3.1. Linear Discriminant Analysis
4.8.1.4. Linear Regression
4.8.1.4.1. Normen
4.8.1.4.2. Nicht-Normen
4.8.2. generative
4.8.2.1. Gaussian Mixture Model
4.8.2.1.1. EM-Algorithmus
4.8.2.2. Hidden Markov Model
4.8.2.3. Bayes
4.8.2.4. Naive Bayes
4.9. Dimensionality Reduction
4.9.1. PCA
4.9.1.1. Kernel PCA