Inhalt:

Bayesche Verfahren der Mustererkennung, Clustering, Expectation Maximization, Neuronale Netze und Lernalgorithmen, Assoziative Netze, Rekurrente Netze. Computer-Vision mit neuronalen Netzen, Anwendungen in der Robotik.

01 - Introduction, notation, k-nearest neighbors
02 - Clustering (kMeans, DBSCAN)
03 - Linear and logistic regression
04 - Model validation
05 - The covariance matrix, PCA
06 - Bagging, decision trees, random forests
07 - Boosting (AdaBoost), Viola-Jones
08 - Perceptron, multi-layer perceptron
09 - Gradient Descent, Backprop, Optimizers (SGD, Adam, RProp)
10 - ConvNets
11 - Unsupervised representation learning I  (VAEs, Glow)
12 - Unsupervised representation learning II (GANs)
13 - RNNs
14 - Attention, Transformers
15 - Attribution, Adversarial Examples