Lecture: Machine Learning

Course Number 17165-01
Lecturers Volker Roth
Assistants Aleksander Wieczorek
Time and Location Tue 10:15 - 12:00; Seminarraum 00.003, Spiegelgasse 1
Wed 14:15 - 16:00; Seminarraum 104, Kollegienhaus
Start 27-02-2018
Exercises Wed 16:15 - 18:00; Seminarraum 104, Kollegienhaus
Prerequisites Knowledge and skills regarding pattern recognition, numerical analysis, and statistics
Objectives Understand the theoretical foundations of Machine Learning

Understand and apply practical learning algorithms: linear and generalized linear models for regression and classification, neural networks, Support Vector machines & kernel methods, mixture models & clustering.

Program in Matlab, Python and Tensorflow
Contents Introduction: What is Machine Learning? Math refresher. Supervised Learning: theoretical foundations. Regression estimation: standard methods + algorithms. Classification: standard methods + algorithms. Neural Networks and Deep Learning. Learning Theory: risk minimization, regularization, elements of statistical learning theory. Kernel Methods. Mixture models. Conditional mixtures (mixtures of experts). Clustering. Bayesian model comparison.
Literature tba
Assessment Lehrveranst.-begleitend
Credit Points 8
Grades 1-6 0,5
Registration Services (Requires login)