Unsupervised Learning
Unsupervised learning is a type of machine learning, where instead of inferring a function from training data that can be used to map new examples, the task is to look for patterns in a data set without pre-existing labels.
The aim of the course is to introduce basic as well as modern concepts of statistical learning without training data (unsupervised statistical learning), with applications in statistical data analysis. Central concepts covered include similarity measures, linear and nonlinear methods of dimensional reduction, centroid, distributional and density-based methods of cluster analysis, hierarchical methods and different validation methods.
The course replaces the previous course with the same name and course code MT7039, and so cannot be included in the same degree as MT7039.
-
Course structure
The course consists of two modules, theory and hand-in assignments.
Teaching format
Instruction is given in the form of lectures, exercise sessions and supervision.
Assessment
Assessment takes place through a written exam, and home exam of the hand-in assignments.
Examiner
A list of examiners can be found on
-
Schedule
The schedule will be available no later than one month before the start of the course. We do not recommend print-outs as changes can occur. At the start of the course, your department will advise where you can find your schedule during the course. -
Course literature
Note that the course literature can be changed up to two months before the start of the course.
Hastie, Tibshirani & Friedman: The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed). Springer.
Bishop: Pattern Recognition and Machine Learning. Springer.
Lee & Verleysen: Nonlinear Dimensionality Reduction. Springer.
Articles.
-
More information
-
Contact