Winter 2020/2021
Bachelor / Undergraduate
Lectures/Vorlesungen
Datenzentrierte Informatik
Bachelor BA-INF 035
Einführung in Datenbanken und Maschinelles Lernen
Lecturers: Prof. Dr. Christian Bauckhage
Contact: Dr. Pascal Welke
Details
Start date: 2020-11-02 (change!)
Time: Mo 14-16 (every week), Fr 14-16 (every second week)
Exercise time: tba
Exercise place: online
Tutors:
- Karla Beckert
- Andrea Cremer
- Alina Hakoupian
- Christian Nickel
- Peter Röseler
Organisation & Materialien
- Vorlesungsunterlagen und Übungszettel werden auf eCampus zur Verfügung gestellt.
- Die Vorlesung ist eine 3+1 Stunden Veranstaltung. Wir werden im zweiwöchigen Wechsel zwei Vorlesungen (Montags und Freitags) bzw. eine Vorlesung (Montags) und eine Übung abhalten. Die Übungstermine werden Anfang Oktober festgelegt.
Wichtige Termine
- Bitte melden Sie sich bis zum 01.11.2020 im eCampus Kurs an. Links zu den Vorlesungen und Übungen werden dort zur Verfügung gestellt.
- 1. Prüfung: 16.2.2021 10.00h (24h Klausur)
- 2. Prüfung: 6.4.2021 10.00h (24h Klausur)
Ablauf der Klausuren
- Die Prüfung beginnt am 6.4.2021 um 10.00h CET. Die angemeldeten Studierenden erhalten zu Beginn der Prüfung eine Email an ihre Universitätsemailadresse.
- Die Prüfung umfasst sechs Aufgaben die auf zwei Stunden Bearbeitungszeit ausgelegt sind.
- Sie müssen Ihre Lösungen innerhalb von 24 Stunden nach Beginn der Prüfung einreichen. Lösungen, die nach 10:00h CET am 7.4.2021 eingehen, können nicht akzeptiert werden. Das bedeutet, dass Sie die Prüfung nicht bestehen, wenn Sie Ihre Lösungen nach 10:00h CET am 7.4.2021 einreichen.
- Es gibt für diese Prüfung keine Beschränkung auf Hilfsmittel oder Materialien. Sie dürfen alle Materialien aus der Vorlesung, den Übungen oder dem Internet verwenden. Sie dürfen aber während der 24 Stunden der Prüfung mit niemanden außer den Dozenten über die Aufgaben und Lösungen dieser Prüfung kommunizieren. Dies schließt unter anderem Ihre Kommilitonen oder das Stellen von entsprechenden Fragen zum Beispiel auf StackOverflow ein.
- Zu Beginn der Bearbeitungszeit von 10.00h–12.00h am 6.4.2021 können Sie Verständnisfragen zu den Aufgaben und dem Ablauf der Prüfung in einem zoom Meeting stellen.
Projektgruppen
Wissensentdeckung und Maschinelles Lernen
Bachelor BA-INF 051
In dieser Projektgruppe werden grundlegende Algorithmen aus den Bereichen Wissensentdeckung und Data Mining erarbeitet, diskutiert, implementiert und empirisch evaluiert.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal Welke, Florian Seiffarth, Till Schulz
Contact: Till Schulz
Supervisors: tba
Details
Time: Vorbesprechung am 03.11.2020 14:00-16:00
Participants: Maximal 6
Beschreibung:In der Projektgruppe werden grundlegende Algorithmen aus den Bereichen Maschinelles Lernen, Wissensentdeckung und Data Mining 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
- Vorbesprechung: 03.11.2020 14:00-16:00
- Bitte registrieren Sie sich im ecampus Kurs bis zum 03.11.2020, um an der Vorbesprechung teilzunehmen. Wir werden dort einen Link und alle weiteren Informationen bereitstellen.
Master / Graduate
Lectures/Vorlesungen
Intelligent Learning and Analysis Systems: Machine Learning
Master: MA-INF 4111
Introductory course to machine learning.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath
Exercises: Eike Stadtländer
Contact: Dr. Tamas Horvath
Details
Start date: 2020-11-06
Time: Fr 12:15-13:45 s.t.
Exercise time: Fr 14:00-15:30 s.t.
Exercise place: online
Tutors: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 (Machine Learning) 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 Data Mining module taught in the summer 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 Machine Learning module in particular, we will give a practically oriented introduction into the most popular methods from Machine Learning as a subfield of Intelligent Learning and Analysis Systems. We will get to know decision tree methods, instance-based learning, artificial neural networks, probabilistic learning, regression methods, kernel methods and support vector machines, and reinforcement learning for intelligent agents. This will be complemented with lectures on the most important approaches within computational learning theory. Within the exercises, it is possible to try out the most important methods and popular Machine Learning systems.
Course Organization & Materials
- Materials are available via eCampus. You must enroll in eCampus on or before November 5 (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. (We
don't release the list of participants for privacy reasons.) In this
case, please send an email with subject "ILAS2021: Excercise Groups" to Fouad Alkhoury, Alexander Zorn, and Dr. Tamas Horvath with the name (surname, given name) and email addresses of all group members before 2020-11-05, 12:00 o'clock. Otherwise, you will be added to some group at random and informed about your group via email on 2020-11-05. Please check your emails on 2020-11-05 evening for your exercise class and tutor.
Important Dates
-
exam (1st try): tba
-
exam (2nd try): tba
Learning from Non-Standard Data
Master: MA-INF 4303
This lecture introduces a selection of machine learning and data mining algorithms developed for graphs and relational structures.
Lecturer: Dr. Tamas Horvath
Contact: Dr. Tamas Horvath
Details
Start date: 2020-11-04
Time: Wed 14:15-15:45
Exercise time: Wed 16:00-17:30
Exercise place: online
Tutor: Richard Palme
Description:
Traditional machine learning and data mining algorithms are resorted to data that can be represented by a single table of fixed width; the rows and the columns correspond to objects and object attributes, respectively. This assumption turns out to be quite restrictive in numerous practical applications involving structured data, such as graphs or relational structures. The lecture will cover the basics of learning and mining graph structured data and relational structures. We will present various algorithms for this setting and analyse their computational properties. We will also discuss some interesting applications in bioinformatics, computational chemistry, and natural language processing.
Course Materials
- Materials are available via eCampus. You must enroll in eCampus on or before 2020-11-04 (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. (We don't release the list of participants for privacy reasons.) In this case, please send an email with subject "LNSD2021: Excercise Groups" to Richard Palme and Dr. Tamas Horvath with the name (surname, given name) and email addresses of all group members before 2020-11-04, 23:59 o'clock. Otherwise, you will be added to some group at random and informed about your group via email on 2020-11-05. Please check your emails on 2020-11-05 evening for your exercise group.
Important Dates
-
exam (1st try): tba
- exam (2nd try): tba
Pattern Recognition (I)
Master: MA-INF 4229
Lecturer: Dr. Nico Piatkowski, Prof. Dr. Christian Bauckhage
Contact: Dr. Nico Piatkowski
Exercises: Sebastian Müller
Details
Start date: 2020-11-02
Time: Mon & Thu, 10.15-11.45
Place: online
Exercise time: Mon 16.15-17.45
Exercise place: online
Description:
The following topics are covered in this lecture:
-
uni-/ multi-variate (non-)linear Regression
-
(non-)linear Classification
-
Bayesian Methods
-
k-Nearest Neighbors. kD-trees
-
Bias-Variance-Dilemma
-
Hoeffding inequality, Vapnik-Chervonenkis inequality & dimension
-
k-Means in hard and soft forms
-
Gaussian Mixture Models
-
EM-Algorithm
-
Linear/ Quadratic/ Fisher Discriminant Analysis
-
Linear Dimensionality Reduction
-
Lagrange Multipliers and Duality, Karush-Kuhn-Tucker Conditions
-
Gradient Methods
-
Constrained Optimization
-
Support Vector Machine
-
Kernels
-
Perceptrons, Feed Forward/ Recurrent Neural Networks and their training
-
Ressource-consumption of ML Systems
Course Materials
Mining Media Data
Study Period: Graduate / Hauptstudium
Lecturer: Dr. Rafet Sifa and Prof. Dr. Christian Bauckhage
Contact: Dr. Rafet Sifa
Details
Start date: 2020-10-27
Time: Tue 16.30-18, Wed 9.30-11
Place: online
Exercise time: Mon 16-17.30
Course Materials
Materials are available here
Seminars/Seminare
Principles of Data Mining and Learning Algorithms
Master: MA-INF 4209
(New: Format has changed!) In this seminar we will read several selected topics concerning machine learning and data mining theory and applications from the deep learning book by Goodfellow, Bengio and Courville. We will meet every two weeks via BigBlueButton summarize the topic from two weeks before and present a new topic.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal Welke
Contact: Florian Seiffarth
Prerequisites: MA-INF 4111 / MA-INF 4112 highly recommended
Details
Time: (see below)
Place: online
Participants: Max. 14
Course Materials
Important Dates
-
preliminary meeting: Monday, 26.10.2020, 10 - 12 (mandatory), ZoomLink to the meeting.
-
seminar meetings: every two weeks, exact day and time tba.
-
seminar writeup deadline: tba.
Labs/Praktika
Lab Development and Application of Data Mining and Learning Systems:
Data Science and Big Data
Master: MA-INF 4306
In this lab, machine learning and data mining techniques are implemented and used in a wide range of applications.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, PD Dr. Michael Mock, Dr. Pascal Welke
Contact: Dr. Pascal Welke
Supervisors: Michael Mock, Florian Seiffarth, Daniel Trabold, Dorina Weichert, Pascal Welke
Prerequisites: MA-INF 4212 highly recommended
Details
Time: (see below)
Place: online
Participants: Max. 6
Course Materials
Important Dates
-
Please register in the ecampus course until 2020-10-26, to be able to attend the preliminary meeting. We will make a link available there.
-
Preliminary Meeting: 2020-10-27 13.00h - 15.00h (online).
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, humor research, constructing scenario using Blender, ...
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: around. 10
Course Materials
- Are available via eCampus.
- Read how to access eCampus
Important Dates
-
preliminary meeting: 23.10.2020 9:30h-12:30h, 14:00h-16:30h (mandatory)
- mid-term presentation: t.b.d. (mandatory)
- final presentation: t.b.d. (mandatory)
- lab report deadline: t.b.d. (preliminary version: one day before final presentation; final version: one week after final presentation)