Description:

Statistical learning is a field that teaches students how to analyze and interpret data by applying statistical methods and machine learning algorithms to uncover patterns, make predictions, and gain insights from data.

The course is designed for master's or PhD. students. Due to the significant programming component, prior knowledge in R or other programming languages is desirable but not required.

Outline:

The syllabus includes: statistical and machine learning methods, in particular: linear and polynomial regression, logistic regression and linear discriminant analysis; cross-validation and the bootstrap, model selection and regularization methods (ridge and lasso); nonlinear models, splines and generalized additive models; tree-based methods, random forests and boosting; support-vector machines. Some unsupervised learning methods are discussed: principal components and clustering (k-means and hierarchical).

Methods of Assessment:

Report and Presentation.

Formalities:

02.05 Preliminary meeting, via Zoom.
23.05 In-person lecture, R12 R07 A79.
24.05 Lecture,  R12 R06 A52  or/and hybrid.
06.06 Lecture, hybrid.

The zoom-link for the preliminary meeting: uni-due.zoom-x.de/j/64874629254.

In-person meetings can be accessed via live-stream.

There are a total of 5-6 tutorials scheduled, each on Fridays from 8.30-12 a.m., starting on 07.06.

The Moodle password is: StatLearn24

For additional information on the exercise, please see the corresponding entry.

Links:

General Information on the module can be found in the course catalogue