Angewandte Foundation Models

Modulnummer: Q06-30
Englischer Titel: Applied Foundation Models
Leistungspunkte: 6
Lehrperson: Chen

Empfohlene Vorkenntnisse

Programming skills in Python; Basic machine learning concepts and techniques.

Zwingende Voraussetzungen

None

Inhalt

Foundation models are large-scale machine learning models trained on broad datasets that can be adapted to a wide range of downstream tasks and application domains. This course introduces the foundations, training, adaptation, evaluation, and practical use of modern foundation models. Students will first study self-attention and Transformer architectures, followed by foundation model pretraining and fine-tuning techniques. The course will then cover methods for evaluating and deploying foundation models, as well as multimodal foundation models that integrate different types of data such as text, images, and other modalities. In addition to general-purpose models, the course will introduce representative foundation models from different application domains, such as earth observation and biomedical. The course combines lectures with practical group work, in which students will learn implement, adapt, and fine-tune selected foundation models for specific tasks using public datasets. The course will be held in English.

Erforderliche Arbeitsleistungen für LP-Vergabe und Prüfungszulassung

- Berichte und Vorträge zu Forschungsprojekten

Lehrveranstaltungen

Vorlesung: 2 SWS 2 LP
Übung: 2 SWS 3 LP
MAP: 1 LP

Zugeordneter Vertiefungsschwerpunkt

Algorithmen und Modelle: nein
Modellbasierte Systementwicklung: ja
Daten- und Wissensmanagement: ja
Ohne Vertiefungsschwerpunkt: nein

Sprache im Modul

Deutsch: nein
Englisch: ja

Angeboten für Studiengänge

M. Sc.: ja
M. Ed.: ja
Wirtschaftsmaster: ja

Angeboten im

Wintersemester: nein
Sommersemester: ja

Turnus

Unregelmäßig