WS 2016/2017 (310003/310013) Machine Learning: Unsupervised Methods Lecture and Tutorial Prof. Dr. Laurenz Wiskott

Lecture (2 SWS, 2 credit points): Tuesdays 12:15-13:45 in NB 3/57. First time 18.10.2016.
Tutorial (4 SWS, 4 credit points): Tuesdays 09:00-12:00 in NB 3/57. First time 25.10.2016.

Language: This course will be given in English.

Goals: (i) The students should get to know a number of unsupervised learning methods. (ii) They should be able to discuss which of the methods might be appropriate for a given data set. (iii) They should understand the mathematics of these methods.

Content: This course covers a variety of unsupervised methods from machine learning such as principal component analysis, independent component analysis, vector quantization, clustering, self-organizing maps, growing neural gas, Bayesian theory and graphical models. We will also briefly discuss reinforcement learning.

Format: This course is given with the flipped/inverted classroom concept. The students work through online material, this will then be deepened in the tutorial with some exercises and then deepened further in the lecture with some general discussion. The exercises are solved in the tutorial in a group effort, not at home, which is the reason why it takes 3 hours rather than the usual 1.5 hours.

Requirements: The mathematical level of the course is mixed but generally high. The tutorial is almost entirely mathematical. Mathematics required include calculus (functions, derivatives, integrals, differential equations, ...), linear algebra (vectors, matrices, inner product, orthogonal vectors, basis systems, ...), and a bit of probability theory (probabilities, probability densities, Bayes' theorem, ...).

Exam: The course will be concluded with an oral exam. The dates will be set in one of the last tutorials.

Schedule