Winter 2022/2023
Bachelor / Undergraduate
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, Vanessa Toborek
Contact: Vanessa Toborek
Details
Time: Vorbesprechung am 12.10.2022 14:00-16:00
Place: Friedrich-Hirzebruch Allee 5 - Hörsaal 4
Participants: Maximal 6
Beschreibung:In den Projektgruppen 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: 12.10.2022 um 14:00-16:00 in Hörsaal 4.
- Bitte registrieren Sie sich im ecampus Kurs bis zum 11.10.2022, um an der Vorbesprechung teilzunehmen. Wir werden dort alle weiteren Informationen bereitstellen.
(Computer) Science Communication
Bachelor BA-INF 051
Diese Projektgruppe wird erstmalig angeboten. Auch hier werden grundlegende Algorithmen aus den Bereichen Wissensentdeckung und Data Mining erarbeitet und diskutiert. Im Mittelpunkt steht allerdings die Erarbeitung der Inhalte für verschiedene Zielgruppen. Die Aufgabe der Studierenden ist die Vermittlung von Wissen in Form eines Coding Nuggets als praktische Anleitung für Fachleute als auch in Form eines Blog Beitrags für interessierte Laien.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal Welke, Florian Seiffarth, Vanessa Toborek, Sebastian Müller
Contact: Vanessa Toborek
Details
Time: Vorbesprechung am 12.10.2022 14:00-16:00
Place: Friedrich-Hirzebruch Allee 5 - Hörsaal 4
Participants: Maximal 6
Beschreibung:In den Projektgruppen 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 wird eine schriftliche Ausarbeitung in zweierlei Form für zwei unterschiedliche Zielgruppen erstellt: Fachleute und interessierte Laien. Dabei wird auf die unterschiedlichen Anforderungen bei der Wissenvermittlung für unterschiedliche Zielgruppen eingegangen.
Kursmaterialien
Wichtige Termine
- Vorbesprechung: 12.10.2022 um 14:00-16:00 in Hörsaal 4.
- Bitte registrieren Sie sich im ecampus Kurs bis zum 11.10.2022, um an der Vorbesprechung teilzunehmen. Wir werden dort 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: 2022-10-21
Time: Fr 12:15-13:45
Place: B-IT Lecture Hall, Room 0.109, Friedrich-Hirzebruch-Alle 6
Exercise time: Fr 14:00-15:30
Exercise place: B-IT Lecture Hall, Room 0.109, Friedrich-Hirzebruch-Alle 6
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
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
Exercises: Fouad Alkhoury
Contact: Dr. Tamas Horvath
Details
Start date: 2022-10-19
Time: Wed 14:15-15:45
Place: CP1-HSZ / Hörsaal 4
Exercise time: Wed 16:00-17:30
Exercise place: Online
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 Organization & Materials
Important Dates
-
exam (1st try): tba
- exam (2nd try): tba
Foundations of Quantum Computing
MA-INF 1107
Quantum computing harnesses quantum mechanical phenomena for information processing. For certain problems, this promises levels of efficiency unattainable on digital computers. Since prototypes of working quantum computers have now become available, it therefore seems reasonable to expect quantum computing to play an increasingly important role in the near future.
This lecture introduces the basic ideas and theoretical concepts behind quantum computing. To begin with, we study simple model systems from quantum mechanics to be able to appreciate "quantum weirdness". We also revisit Boolean algebras and Boolean functions to better understand how classical information processing differs from quantum information processing. We then study quantum bits (qubits), their properties, and the mathematics that describes their behavior. Finally, we study adiabatic quantum computing and its applications and conclude with a first look at quantum gate computing and its fundamentals.
Lecturer: Prof. Dr. Christian Bauckhage
Contact: Prof. Dr. Christian Bauckhage
Exercises: Patrick Seifner
Details
Start date: 2022-10-10
Time: Mondays 10.15-12.45
Place: Hörsaal II, Meckenheimer Allee 176
Exercise time: Mondays 14:15-15:45, every two weeks starting from 2022-10-24
Exercise place: B-IT Seminarraum 1.047
Course Materials
Important Dates
- Don't forget the course registration deadline in BASIS, which is usually in November.
- first exam: 6.2.2023 from 17:00 till 19:00; Place: HS 1 and 2 of Hörsaalzentrum Poppelsdorf (Friedrich-Hirzebruch-Allee 5) (Attention: NOT Meckenheimer Allee 176)
- second exam: 27.3.2023 from 15:30 till 17:30; Place: HS 1 and 2 of Hörsaalzentrum Poppelsdorf (Friedrich-Hirzebruch-Allee 5) (Attention: NOT Meckenheimer Allee 176)
Graph Representation Learning
MA-INF 4316
We will discuss general approaches for machine learning (ML) on graph structured data. In particular, computational methods for graph representation learning such as graph neural networks (GNNs), graph kernels, as well as graph mining techniques will be discussed, analyzed, and applied. Regarding GNNs and graph kernels, we will discuss the expressive power and how these concepts are related, as well as several specific examples. In the area of graph mining, we will likely investigate fast (approximate) algorithms to count small patterns, such as triangles, or trees. If time permits, we might venture into the realm of ranking on large-scale graphs, with applications such as recommender systems. The exercises will focus on practical implementations and the application of these methods to real world examples.
Lecturer: Dr. Pascal Welke
Contact: Dr. Pascal Welke
Exercises: Till Schulz
Tutor: Lukas Conrads
Details
Start date: 2022-10-10
Time: Mondays 12.15-13.45
Place: Hybrid (HS 5+6, Hörsaalzentrum Poppelsdorf, Friedrich Hirzebruch Allee 5)
Exercise time: Tuesdays 16.15-17.45
Exercise place: (INF / B-IT / Seminarraum 1.047, Informatik III, Friedrich Hirzebruch Allee 8)
Course Materials
I am planning to give this lecture in a hybrid fashion: I will be present in the lecture hall and will stream the presentation and audio live via zoom. You may join physically or virtually.
Important Dates
- Don't forget the course registration deadline in BASIS, which is usually in November.
- first exam: tba
- second exam: tba
Advanced Methods For Text Mining
Besides being a collection of characters, text is up until now still considered to be one of the most commonly used medium of communication. The complex nature of textual data as well as their sheer amount though make building data mining models challenging. As part of the Master's Program in Media Informatics at the Bonn-Aachen International Center for Information Technology (B-IT), this course will cover the state-of-the-art and established methods for mining textual datasets . The course will start with a lecture series on the preliminaries of data mining and machine learning, continue with a deep dive on advanced text mining methods involving Latent Semantic Indexing, Word Embeddings, conventional and resource efficient Recurrent Neural Networks for sequential representations from textual data, Attention Mechanism as well as Transformer architectures and end with lectures on applications from real wold involving natural language inference and information extraction in financial documents, recommender systems in the legal and audit domain and generative models for digital forensics.
Lecturer: Dr. Rafet Sifa
Contact: Dr. Rafet Sifa
Details
Start date: 2022-10-27
Time: Thursday 14:00-15:30
Place: Hörsaal 0.109 (B-IT), Friedrich-Hirzebruch-Allee 6
Exercise time: Thursday 12:15-13:45
Exercise place: Hörsaal 0.109 (B-IT), Friedrich-Hirzebruch-Allee 6
Course Materials
Basic knowledge of AI, data science, machine learning, and pattern recognition; programming skills; good working knowledge in statistics, linear algebra, and optimization. Having taken the related B-IT courses Mining Media Data I and Mining Media Data II is not a must. The course has 4-ETCS credits (with 2+2 SWS) and is taught by Dr. Rafet Sifa. The teaching assistant of the course will be Tobias Deußer. One week prior to each lecture a list of recommended readings (from text books, reports and research papers) related to the course work will be announced. For questions as well as the registration (see the news below) please write to [Email protection active, please enable JavaScript.].Important Dates
- first exam: tba
- second exam: tba
Seminars/Seminare
Principles of Data Mining and Learning Algorithms - Selected Papers from ML Conference
Master: MA-INF 4209
In this seminar we will focus on a selected few papers from the NeurIPS conference, which is one of the premier conferences in machine learning. The seminar consists of a discussion meeting, and one final presentation meeting, which will simulate a scientific conference with paper presentations.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal Welke, Fouad Alkhoury
Contact: Fouad Alkhoury
Details
Time: (see below)
Place: online
Participants: Max. 6
Course Materials
- Are available via ecampus
- Read how to access eCampus
Important Dates
-
preliminary meeting: 2022-10-18 10:00h - 11:00h (online)
-
Please register in the ecampus course until 2022-10-17. We will make a link to the meeting available on ecampus.
Principles of Data Mining and Learning Algorithms: Ethics in AI
Master: MA-INF 4209
Ethics is an increasingly important topic in all areas of AI. It raises many fundamental questions about both the researchers/developers implementing AI systems (e.g., "how to collect training and test data without violating anyone's privacy?) as well as the AI systems as moral agents themselves (see, e.g., the famous trolley problem for autonomous vehicles). In this seminar, you take on a role in an (imaginary) committee whose objective it is to constitute a new MSc. in Artificial Intelligence. Your specific task is to decide if ethics should be integrated into the programme and if so what should be taught and how should it be taught. For that purpose, we will read and discuss official guidelines, research papers, and book excerpts about ethics in artificial intelligence.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, Dr. Pascal Welke, Sebastian Müller, Vanessa Toborek, Eike Stadtländer
Contact: Dr. Pascal Welke
Details
Schedule (tentative!): monthly on a Tuesday
- Nov 08: Orientation
- Nov 15: Literature Meeting
- Nov 22: Presentation & Discussion
- Dec 06: Presentation & Discussion
- Dec 13: Presentation & Discussion
- Jan 17: Presentation & Discussion
Time: 14:15 s.t.
Place: Room 3.110
Participants: max. 8
Course Materials
Important Dates
-
preliminary meeting: 2022-10-18 14:00h - 15:00h - Room 3.110
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: Sebastian Müller
Supervisors: Michael Mock, Sebastian Müller
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 2022-10-18.
-
Preliminary Meeting: 2022-10-19 14.00h - 16.00h (online).
Lab Development and Application of Data Mining and Learning Systems: Understanding and Applying Neural ODEs
Master: MA-INF 4306
In this lab we will study the Neural Ordinary Differential Equations
(Neural ODE) approach (https://arxiv.org/abs/1806.07366) to the
modelling of probability distributions that are define continuously in
time. Specifically, we will model time series data as Markov Jump
Processes (MJP).
We will start by discussing the Neural ODE paper in some detail, as well
as the basics of MJPs. Then we will use ideas from Generative
Adversarial Networks (GAN) and Wasserstein Autoencoders (WAE) to fit
MJPs, modelled via Neural ODEs, to time series data.
Lecturers: Prof. Dr. Stefan Wrobel, Dr. Tamas Horvath, PD Dr. Michael Mock, Dr. Pascal Welke, Dr. Ramses Sanchez
Contact: Dr. Ramses Sanchez
Supervisors: Dr. Ramses Sanchez
Details
Time: 6-week long Lab starting from February 13 until March 27
Place: Tba
Participants: Max. 6
Further details: We plan to meet once a week, starting on Monday, February 13. We shall discuss the theory behind Neural ODEs and MJPs in the first two meetings. The other three meetings will be to discuss issues/questions you might have with either the coding or the math. Since we are doing only 6 weeks, we expect you to work full time on the lab.
Course Materials
Important Dates
-
First meeting, February 13, 10am, b-it room 3.110: Introduction to Neural ODEs
-
2nd meeting, February 17, 10am, b-it room 3.110: Introduction to MJPs
- Last meeting, March 27, 10am, b-it room 3.110: Final presentations/discussions