You are here: Home Teaching

Summer 2021

Bachelor / Undergraduate

Projektgruppe

Wissensentdeckung und Maschinelles Lernen
Bachelor BA-INF 051

In dieser Projektgruppe werden grundlegende Algorithmen aus dem Bereich Maschinelles Lernen erarbeitet, diskutiert, implementiert und empirisch evaluiert.

Study Period: Undergraduate / Grundstudium

Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal Welke, Vanessa Toborek, Till Schulz

Contact: Till Schulz

Details

Time:     siehe unten

Place:    online

Participants: Maximal 12

Beschreibung:

In der Projektgruppe werden grundlegende Algorithmen aus dem Bereich Maschinelles Lernen vorgestellt. Die Aufgabe der Studierenden ist es, in Kleingruppen jeweils einen Algorithmus zu erarbeiten und einen wissenschaftlichen Vortrag darüber zu halten. Im Anschluss soll der Algorithmus implementiert und evaluiert werden. Neben einem Abschlussvortrag soll eine schriftliche Ausarbeitung erstellt werden.

Kursmaterialien

Wichtige Termine

  • Die Vorbesprechung der Veranstaltungen Projektgruppe Wissensentdeckung und Maschinelles Lernen: Maschinelles Lernen und Projektgruppe Wissensentdeckung und Maschinelles Lernen: Wissensentdeckung werden gemeinsam stattfinden.
  • Vorbesprechungstermin: 14.04.2021  10:00-12:00
  • Bitte registrieren Sie sich im ecampus Kurs bis zum 13.04.2021, um an der Vorbesprechung teilzunehmen. Wir werden dort einen Link und alle weiteren Informationen bereitstellen.


Master / Graduate

Lectures/Vorlesungen

Intelligent Learning and Analysis Systems: Data Mining and Knowledge Discovery
Master: MA-INF 4112

Introductory course to data mining and knowledge discovery.

Study Period: Graduate / Hauptstudium

Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath

Contact: Dr. Tamas Horvath

Details

Start date: 2021-04-23

Time:  Fr 12:15-13:45 s.t.

Place: online

Exercise time:  Fr 14:00-15:30 s.t.

Place: online

Tutors:

   Jelena Trajkovic

Description: 

With more and more data available for analysis and decision making - from web documents and digital media to sensory data from cameras, microphones, and ubiquitous devices - it becomes increasingly more important to understand how such large volumes of data can be analyzed by computers and used as the basis for new intelligent services, for decision making, and for making computers learn from experience. In companies around the world, from retail and banks all the way to Google, intelligent learning and analysis techniques are used to improve business decisions. Likewise, in science, important discoveries are made easier by automated learning methods, and games and other artifacts are being made adaptive with learning technology.

Within the intelligent systems track of the computer science Master's program, intelligent learning and analysis systems are one of the two major topics. This module (Data Mining) is one of the two modules that are offered as an introduction for master's students to Intelligent Learning and Analysis Systems. The other is the Machine Learning module taught in the winter semester. Both modules can be selected in either order, and you may choose to attend one or both of them. For a complete introduction to the topic, it is recommended to attend both modules.

In the Data Mining module in particular, we will focus more on the algorithms for discovering knowledge in large databases and on their technical properties such as scalability. We will get to know scalable variants of the decision tree methods that we have been looking at in the Machine Learning module, and discover algorithms for new Data Mining tasks that we have not been looking at there, in particular clustering, association rule discovery, subgroup discovery, discovery from spatial and geographic data, analysis algorithm for text and web documents, visualization options for data analysis. We will mostly be focusing on practical and algorithmic aspects which can be tried out with popular Data Mining packages, but will also have a chance to look at some of the theory behind the algorithms.

Course Organization & Materials

  • Materials and Zoom links are available via eCampus. You must enroll in eCampus on or before April 23. (Read how to access eCampus)
  • You are allowed to form excercise groups (of at least four and at most five students) if you know other students participating in this course. In this case, please send an email with subject "ILAS2021: Excercise Groups" to Anna Katharina Heuser, Hayal Deniz Özer, and Jelena Trajkovic with the name (surname, given name) and email addresses of all group members before 2021-04-27, 23:59 o'clock (strict). Otherwise, you will be added to some group at random and informed about your group via email on 2020-04-28. Please check your emails on 2020-04-28 evening for your exercise class and tutor.

Important Dates

     exam
    • 1st try: 2021-08-06, 10:00-13:00, online (form and date are tentative!)
    • 2nd try: 2021-09-24, 10:00-13:00, online (form and date are tentative!)

 

Data Science and Big Data
Master: MA-INF 4212

Advanced course on big data analytics and systems.

Study Period: Graduate / Hauptstudium

Lecturer: Dr. Tamas Horvath, PD Dr. Michael Mock

Exercises: Eike Stadtländer, Fouad Alkhoury

Contact: Dr. Tamas Horvath

Details

Start date: 2021-04-21

Time:  Wed 10:15-11:45 s.t.

Place: online

Exercise time: Wed 12:00-13:30 s.t.

Tutors:


Description: 

The course offers an in-depth knowledge of different aspects of big data analytics and systems, including  algorithmic techniques for analyzing structured and unstructured data that cannot be stored in a single computer because it has enormous size and/or continuously arrives with such a high rate that requires immediate processing. In addition to the algorithmic aspects, distributed big data processing and database systems will be presented and applied.

Topics include similarity search,  synopses for massive data, mining massive graphs, classical data mining tasks for massive data and/or data streams, architectures and protocols for big data systems, distributed batch (Hadoop) and stream (Storm) processing systems, non-standard databases for big data (Cassandra).

Course Organization & Materials

  • Materials and Zoom links are available via eCampus. You must enroll in eCampus on or before April 21. (Read how to access eCampus)
  • You are allowed to form excercise groups (of at least four and at most five students) if you know other students participating in this course. In this case, please send an email with subject "DSBD2021: Excercise Groups" to Anna Katharina Heuser and Hayal Deniz Özer with the name (surname, given name) and email addresses of all group members before 2021-04-25, 23:59 o'clock (strict). Otherwise, you will be added to some group at random and informed about your group via email on 2021-04-26. Please check your emails on 2021-04-26 evening for your exercise class and tutor.


Important Dates

  • exam (1st try): 2021-08-04, 10:00-13:00, online (form and date are tentative!)
  • exam (2nd try): 2021-09-22, 10:00-13:00, online (form and date are tentative!)
 
 

Pattern Recognition (II)
Master: MA-INF 4323

Lecturer: Prof. Dr. Christian Bauckhage

Exercises: Sebastian Müller

Details

Start date: April 12th

Time:  Mon & Thu, 10-11.30h

Place: online

Exercise time:  Mon 16.15-17.45h, every two weeks

Exercise place: online

Prerequisites: Pattern Recognition (I) highly recommended

Description:

The lecture will revolve around iterative procedures. Theoretical background in (mostly) linear algebra will be discussed thoroughly. Topics range from a direct application of linear algebra in matrix factorization (eg spectral decomposition) to general optimization principles derived from energy minimization (in eg Hopfield Networks). The latter already hints at a connection to physics which will be embraced to give an introduction to quantum computing during the last weeks of the lecture. The exercises will mostly consist of programming tasks.

Course Organization & Materials

 

Important Dates

  • exam (1st try): July 22, 2021
  • exam (2nd try): tba
 
 

Mining Media Data (II)

Lecturer: Dr. Rafet Sifa

Exercises: Dr. Rafet Sifa

Details

Start date: 2021-04-20 at 16:30h

Time:  Tuesday, 16:30h - 18:00h

Place: online

Exercise time:  Tue 15:00h-16:30h

Exercise place: online

Prerequisites: Mining Media Data (I) is recommended, but not a must.

Description:

The course titled as Mining Media Data II aims at covering state-of-the-art and established data mining methods suited for modeling and extracting patterns from media data. Given their flexibility and success for a variety of media applications, the course will heavily investigate how deep learning can be utilized for representation learning and building predictive and prescriptive data mining models. To that end, the course will start with covering the basics of optimization and data description models and their applications to build recommender systems. Following that, it will successively dive into feed forward, convolutional and recurrent neural networks and their applications to analyze structured and unstructured (new) media data in form of transactions, text and images. Furthermore, the course will touch on numerous real world applications related to business intelligence, digital forensics, behavioral and game analytics as well as recommender systems.

Course Organization & Materials

Important Dates

  • exam (1st try): tba
  • exam (2nd try): tba

Seminars/Seminare

Principles of Data Mining and Learning Algorithms:
Selected Papers from NeurIPS 2020
Master: MA-INF 4209

In this seminar we will focus on a selected few papers from last year's NeurIPS conference, which is one of the premier conferences in machine learning. The seminar consists of two sessions on how to give a talk at a conference, a discussion meeting, and two final presentation meetings, which will simulate a scientific conference with paper presentations. All writing tasks will be organized via EasyChair, a real-world conference management system.

Study Period: Graduate / Hauptstudium

Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal Welke, Eike Stadtländer

Contact: Eike Stadtländer

Supervisors: Florian Seiffarth, Ewald Bindereif, Fouad Alkhoury, Eike Stadtländer

Prerequisites: MA-INF 4111 highly recommended

Details

Time:  see below

Place: online

Participants: Max. 12

Course Materials

Important Dates

  • Please register in the ecampus course until 2021-04-13, to be able to attend the preliminary meeting. We will make a link available there.

Labs/Praktika

Lab Development and Application of Data Mining and Learning Systems: Machine Learning and Data Mining
Master: MA-INF 4306

In this lab, machine learning and data mining techniques are implemented and used in a wide range of applications.

Study Period: Graduate / Hauptstudium

Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal WelkeFlorian Seiffarth

Contact: Florian Seiffarth

Supervisors:  Till Schulz, Florian Seiffarth, Vanessa Toborek, Dr. Daniel Trabold, Dorina Weichert, Dr. Pascal Welke

Prerequisites: MA-INF 4212 highly recommended

Details

Time: (see below)

Place: online (link on ecampus)

Participants: Max. 8

Course Materials

Important Dates

  • The (mandatory) preliminary meeting is on 14.04.2021 at 12 pm. Please register in the ecampus course until 13.04.2021, to be able to attend the preliminary meeting. We will make a link to the meeting available on ecamus.
 

Lab Development and Application of Data Mining and Learning Systems:
AI Language and Vision
Master: MA-INF 4306

In this lab, we will do cutting-edge Machine-Learning AI experiments related with what we look at (vision), what we speak (language), and something in between (knowledge). Topics include Visual Question-Answering, Imposing Structures onto Word-Embeddings, Ball-Embedding for ImageNet

Study Period: Graduate / Hauptstudium

Lecturers: Prof. Dr. Christian Bauckhage, Dr. Tiansi Dong, Dr. Tamas Horvath, Dr. Pascal Welke

Contact: Dr. Tiansi Dong

Prerequisites: MA-INF 4212 highly recommended

Details

Time:  (see below)

Place: online

Participants: Max. 8

Course Materials

Important Dates

  • preliminary meeting:  14. April 14:30h-15:30h (mandatory)
  • 1st presentation: TBA
  • 2nd presentation: TBA
  • final presentation: TBA
  • lab report deadline: final version: one week after final presentation
Document Actions