Statistical learning 1

Master's course

The following skills are developed in the course: - Students are familiar with the functionality of basic algorithms in the field of data science. - Students understand the statistical concepts and working methods behind the algorithms covered. - Students are able to select suitable algorithms for given problems. - Students are familiar with the data structures, runtime specifics and complexity classes required by the algorithms covered. - Students can apply the algorithms in isolated problems.

1st semester: Students have previous knowledge of mathematics/statistics up to 8 ECTS and therefore know simple statistical measures as well as basic statistical test procedures (e.g. t-test). / 2nd semester: No prerequisites / 2nd semester: Module examination MLAL.A1 (Algorithmic 1)

The following content is discussed in the course: - Statistical measures (point and interval estimators) - Statistical test procedures - Grouping algorithms (classification trees, agglomerative hierarchical clustering, etc.) - Regression algorithms (regression trees, random forests, etc.) - Associative algorithms - Procedures for preprocessing data (e.g. principal component analysis)

PRIMARY LITERATURE: - Murphy, K. P. (2012): Machine Learning: A Probabilistic Perspective (Ed. 1), MIT Press, Cambridge (ISBN: 978-0-262-01802-9) - Bishop, C. (2006): Pattern Recognition and Machine Learning (Ed. 1), Springer-Verlag, New York (ISBN: 978-0-387-31073-2) SECONDARY LITERATURE: - James, G.; Witten, D; Hastie, T.; Tibshirani, R. (2013): An Introduction to Statistical Learning: with Applications in R (Ed. 1), Springer Science and Business Media, New York (ISBN: 978-1-461-471387) - Steele, B.; Chandler, J.; Reddy, S. (2016): Algorithms for Data Science (Ed. 1), Springer, Berlin (ISBN: 978-3319457956)

Written exam

German

6

33

3.0

The following methods are used: - Lecture with discussion - Processing of exercises - Interactive workshop

1

Prof. (FH) Dr. Johannes Lüthi, Prof. (FH) Dr. Michael Kohlegger

MLAL.1

integrated lecture

Compulsory

none