Modulcode:	WInf-DMML4
Englische Bezeichnung:	Data Mining and Machine Learning: Basic and Advanced Techniques of Data Analysis
Modulverantwortliche(r):	Prof. Dr. Ansgar Scherp
Turnus:	unregelmäßig (WS15/16 WS16/17 WS17/18)
Präsenzzeiten:	4V 2Ü
ECTS:	8
Workload:	240 Std. (60 Std. Präsenzzeit, 180 Std. Nachbereitung der Vorlesungsinhalte und Übung)
Dauer:	ein Semester
Modulkategorien:	WI (MSc Inf (15)) WWi (MSc WInf (15)) WI (MEd Inf) WPI (MEd Inf) WI (MSc WInf) IG (MSc Inf)
Lehrsprache:	Englisch
Voraussetzungen:

Kurzfassung:

The course introduces to the topic of data mining and machine learning. It presents various different basic and advanced methods of data mining and machine learning, compares them, and shows their applications.

Lernziele:

The students will be enabled to understand, reflect, and apply different methods and techniques in the areas of data mining and machine learning. The students will be able to explain the difference and commonalities of data mining and machine learning. The students will be empowered to decide which method to apply to what kind of problem.

Lehrinhalte:

An introduction to the topic is conducted by giving an overview of the methods in data mining and machine learning. The commonalities and the differences between data mining and machine learning will be explained and discussed. Subsequently different selected basic and advanced methods in data mining and machine learning will be presented. In addition to the theoretical knowledge, some real-world examples of where the methods are appllied will be presented.

The course covers among others:

• Introduction to knowledge discovery and outline of the problem
• Data types
• Clustering of data (partitional / hierarchical)
• Learning of associaton rules from data (basic / advanced / extensions)
• Formal concept analysis (basic / extensions)
• Dimensionality reduction (PCA/SVD)
• Classification of data
• Rule induction
• Naïve Bayes (basic / extensions)
• Language models
• Hidden markov models
• Instance-based classifier
• Regression models
• Artificial neural networks
• Support vector machines
• Ensemble classifier
• Learning to rank
• Schema induction from data

Weitere Voraussetzungen:

Basic knowledge about data engineering.

Prüfungsleistung:

The exam will be oral or in written, depending on the size of the class. Active participation in the tutorials is prerequisite for admission to the exam.

Appendix: In WS 2017/2018, the exam will be written.

Lehr- und Lernmethoden:

Learning material will be provided in form of presentation slides.

Verwendbarkeit:

The acquired knowledge and skills can be applied for a Masters thesis.

Literatur:

Tan, Steinbach, Kumar: Introduction to data mining, Addison Wesley, 2006.

Liu: Web Data Mining, Springer, 2007.

Witten, Frank, Hall: Data Mining, Morgan Kaufmann, 2011.

Verweise:

None.

Kommentar:

None.