Organization (SoSe 25)
- Course
- 3+2 hours weekly (equals 6 ECTS)
- Lecture:
- Prof. Dr. Thomas Seidl
- Assistant:
- Dr. Gabriel Marques Tavares, Mamdouh Aljoud
- Audience:
- Bachelor students in the programs of the Institute for Informatics
- Course Material:
- Moodle
- Prior Knowledge:
- The course expects participants to have basic skills in machine learning and data mining.
- Course Language:
- English
Content
This course explores the world of unsupervised learning, that is, learning from data without label availability. For that, we dive into the clustering task, which aims at grouping similar behavior and identify common patterns in the data. We specifically focus on deep clustering, that is, the combination of clustering with concepts from the field of deep learning. Corresponding methods have become popular in recent years and have achieved very good results on image and text data sets.
The identification of clusters in high-dimensional data sets like images, text, or videos can be very complex as we have to deal with the curse of dimensionality, which describes the phenomenon that samples become more and more similar with an increasing amount of dimensions. For this reason, the clustering task is often accompanied by some kind of feature reduction. In deep clustering, a deep learning-based representation learning method is supplemented by a specific clustering loss.
The course covers these different approaches and how they partition data. Moreover, discussions about the rationale behind the algorithmic creation are fostered, addressing interesting research questions and design decisions.
Prerequisites:
- Basic knowledge of deep learning
- Interest in scientific working
Helpful references:
Deep Clustering Survey 1: Link
Deep Clustering Survey 2: Link
List of Deep Clustering Algorithms: Link
Implementations of Deep Clustering Algorithms: Link