Modulcode:	infMPMaL-01a
Englische Bezeichnung:	Master project - Machine Learning
Modulverantwortliche(r):	Prof. Dr. Peer Kröger
Turnus:	unregelmäßig (SS21 SS23)
Präsenzzeiten:	4P
ECTS:	10
Workload:	300 Std. Projektarbeit, davon 60 Std. betreut
Dauer:	ein Semester
Modulkategorien:	MSc-Inf-Proj (MSc Inf (21)) Proj (MSc Inf (15))
Lehrsprache:	Englisch
Voraussetzungen:

Kurzfassung:

Machine Learning gains increasing attention and significance especially in the context of Big Data and Data Science. Today Data Science and Big Data advance into various facets of our daily life through the application of Machine Learning methods. The purpose of this practical course is to make the students familiar with the practical approach of Machine Learning in the context of Big Data applications and Data Science. By learning the handling with state-of-the-art Machine Learning and Big Data tools the core concepts of the Data Science process are conveyed.

Lernziele:

Lehrinhalte:

Machine Learning gains increasing attention and significance especially in the context of Big Data and Data Science. Today Data Science and Big Data advance into various facets of our daily life through the application of Machine Learning methods. The purpose of this practical course is to make the students familiar with the practical approach of Machine Learning in the context of Big Data applications and Data Science. By learning the handling with state-of-the-art Machine Learning and Big Data tools the core concepts of the Data Science process are conveyed.

The students will work in small teams on real-world Data Science use cases from different domains. Selected Machine Learning approaches (e.g. Deep Learning) will be applied to different data domains, including image, text, point clouds and graphs depending on the particular use case. This way, each team will go through the entire Data Science process from the raw data up to the extraction and interpretation of patterns as "knowledge", typically including the following steps:

• Data integration
• Data preprocessing / data cleaning
• Machine Learning (training, hyperparameter tuning, model selection)
• Visualization

Basic knowledge in Machine Learning and Big Data (e.g. through lectures "Knowledge Discovery and Data Mining", and "Big Data Managament and Analytics") is helpful but not mandatory to attend this module.

Weitere Voraussetzungen:

• Knowledge Discovery and Data Mining

Prüfungsleistung:

Lehr- und Lernmethoden:

Verwendbarkeit:

Literatur:

Verweise:

Kommentar: