# Teaching

Our teaching portfolio comprises various courses addressing the foundations of data science and machine learning in complex data. Below you find information on lectures, seminars, and labs that we currently offer at University of Würzburg. The course description is provided in the language in which the course is held.

Lectures start in the first week of the teaching period. For seminars and labs, an information event is held in the beginning of the teaching period. For further information, please refer to the linked Moodle courses.

** BSc Vorlesung "**Algorithmen, KI und Data Science 2"

Prof. Dr. Ingo Scholtes

4 SWS, 08 110200, Mo + Mi 14-16 Turing

Die Vorlesung kombiniert eine Reihe von Vorlesungen - die grundlegende Konzepte und Algorithmen in der Informatik, KI und Data Science vorstellen - mit wöchentlichen Übungen, die zeigen, wie wir diese Algorithmen in Python implementieren und anwenden können. Das Kursmaterial besteht aus Vorlesungsfolien und Jupyter-Notebooks. Die Studierenden können ihr Wissen anhand von wöchentlichen Übungsblättern anwenden und vertiefen.

**BSc Übung "**Algorithmen, KI und Data Science 2"

Lisi Qarkaxhija, Franziska Heeg, Moritz Schüler

2 SWS, 08 110250, 2 St, Di 8-10 SE 2, Mi 10-12 SE III, Do 10-12 SE 3

**MSc Lecture "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes

2 SWS, 08 130000, WED 12-14 HS2

This lecture is a direct follow-up of our course "Statistical Network Analysis". In a first chapter we discuss machine learning applications of statistical network models covered in our SNA course. We then turn our attention to state-of-the-art graph representation learning techniques and graph neural networks. Just like for "Statistical Network Analysis", the lectures will integrate practice session in python, in which we demonstrate how to apply the methods. While completing the course Statistical Network Analysis before is certainly beneficial, this course can also be taken independently.

**MSc Exercise "Machine Learning for Complex Networks"**

Dr. Vincenzo Perri, Chester Tan

2 SWS, 08 130050, MO 10-12, THU 10-12, FR 10-12

**MSc Praktikum (Lab) "Graph Neural Networks"**

Prof. Dr. Ingo Scholtes

6 SWS, 08 140720, biweekly meetings, block session at the end of the semester

In this lab, you get the chance to take a deep dive into recent machine learning techniques for graph-structured data. We have a collection of interesting recent works on graph neural networks, from which you can choose. Your goal will be to implement those works to address a practical machine learning task.

**MSc eXtAI Lab 1**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

6 SWS, 08 181090

**BSc/MSc Seminar "Data, AI, and Society"**

Dr. Anatol Wegner, Chester Tan

2 SWS, 08 151250, biweekly meetings, block session at the end of the semester

In this seminar, we discuss current societal challenges and opportunities in the application of data science and machine learning. Following an information event at the beginning of the lecture period, the seminar will be organized as a block seminar in the format of a mini-conference. For the final event, students will have to prepare selected works dicussing societal consequences of Big Data and artificial intelligence.

**BSc/MSc Seminar "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes, Franziska Heeg, Lisi Qarkaxhija

2 SWS, 08 151260, biweekly meetings, block session at the end of the semester

In this seminar, we will discuss recent advances in the application of machine learning to graph-structured data. Following an information event at the beginning of the lecture period, we will hold a block seminar in the format of a mini-conference. For this, students will have to prepare selected works on machine learning techniques and applications in data on complex networks.

**Obserseminar (Research Seminar) "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes

2 SWS, 08 153000

**MSc Lecture Statistical Network Analysis**

*I=AKIS-1V / I=AKIS-1Ü*

Prof. Dr. Ingo Scholtes (Lecture), Franziska Heeg, Lisi Qarkaxhija, Chester Tan (Exercises)

2+2 SWS, Wednesday 12-14 (Lecture), Monday 10-12, Wednesday 10-12, Friday 10-12 (Exercises)

This course introduces fundamental concepts for the statistical modelling of complex networks and shows how to apply them to practical network analysis tasks. Topics covered include foundations of graph theory, centrality and modularity measures, aggregate statistical characteristics of large networks, random graphs and statistical ensembles of complex networks, generating function analysis of expected graph properties, scale-free networks, stochastic dynamics in networks, spectral analysis, as well as the modelling of time-varying networks. The course material consists of annotated slides for lectures as well as a accompanying git-Repository of jupyter notebooks, which implement and validate the theoretical concepts covered in the lectures. Students can test and deepen their knowledge through weekly exercises. The successful completion of the course requires to pass a final written exam.

**MSc Lecture Introduction to Informatics for Jurists**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner

*10-I=DigL01-222-m01*

2+2 SWS, Tuesday 18-20 (Lectures), Exercises upon arragement

This course introduces fundamental concepts of computer science for students in the LL.M. program Digitalization and Law at the Faculty of Law. Introducing both technical aspects of computing, programming, as well as computational and algorithmic thinking, the course covers topics like Algorithms and Data Structures, Introduction to Programming, Encryption, Data Protection and Security, Communication Networks, Internet Technologies, and Cloud Computing. The successful completion of the course requires to pass a final written exam.

**MSc Lab** **Computational Astrophotography**

Prof. Dr. Ingo Scholtes, Prof. Dr. Radu Timofte, Franziska Heeg

*I=PRAK-1P*

6 SWS, Time upon arragement

This lab introduces computational aspects in the photographic imaging of astronomical objects. After a first introduction into astronomical equipment, guiding, and deep sky astrophotography, we will use a computer-controlled telescope and advanced astronomical cameras to collect narrow-band image data on deep sky objects like nebula or galaxies. These imaging sessions will take place outside on campus in the evening, precise dates depend on the weather situation. In a second phase of the lab, students will write python code to address key image processing tasks such as image registration and stacking, debayering of narrow-band data, stretching, and exposure integration. The successful completion of the lab requires to write code and a written report.

**MSc Lab** **Graph Neural Networks**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

*I=PRAK-1P*

6 SWS, Time upon arragement

**MSc Lab** **Social Network Analysis**

Prof. Dr. Ingo Scholtes

*I=PRAK-1P*

6 SWS, Time upon arragement

**MSc Lab** **Interpretability and Explainability in Deep Learning**

Chester Tan, Lisi Qarkaxhija, Prof. Dr. Ingo Scholtes

*I=PRAK-1P*

6 SWS, Time upon arragement

**eXtAI Lab** **Network Analytics and Visualisation Lab**

*xtAI=L1*

Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

3-6 SWS

**BSc Lab** **KI und Data Science Lab 1**

*I_KIDS-Lab1-1P*

Prof. Dr. Goran Glavas, Prof. Dr. Ingo Scholtes

6 SWS

**BSc/MSc Seminar Data, AI, and Society**

*I-SEMx-1S*

Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

2 SWS, Time upon arragement

**MSc Seminar Social Network Analysis**

*I-SEMx-1S*

Prof. Dr. Ingo Scholtes

2 SWS, Time upon arragement

**MSc Seminar Interpretability and Explainability in Deep Learning**

*I-SEMx-1S*

Chester Tan, Lisi Qarkaxhija, Prof. Dr. Ingo Scholtes

2 SWS, Time upon arragement

**Oberseminar (Research Seminar) Machine Learning for Complex Networks **

Prof. Dr. Ingo Scholtes

2 SWS,

**MSc Lecture "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes

2 SWS, 08 130000, WED 12-14 HS2

This lecture is a direct follow-up of our course "Statistical Network Analysis". In a first chapter we discuss machine learning applications of statistical network models covered in our SNA course. We then turn our attention to state-of-the-art graph representation learning techniques and graph neural networks. Just like for "Statistical Network Analysis", the lectures will integrate practice session in python, in which we demonstrate how to apply the methods. While completing the course Statistical Network Analysis before is certainly beneficial, this course can also be taken independently. A syllabus of the course is available here

**MSc Exercise "Machine Learning for Complex Networks"**

Dr. Anatol Wegner, Franziska Heeg, Lisi Qarkaxhija, Chester Tan

2 SWS, 08 130050, MO 10-12, THU 10-12, FR 10-12

**MSc Praktikum (Lab) "Graph Neural Networks"**

Prof. Dr. Ingo Scholtes, Franziska Heeg

6 SWS, 08 140720, biweekly meetings, block session at the end of the semester

In this lab, you get the chance to take a deep dive into recent machine learning techniques for graph-structured data. We have a collection of interesting recent works on graph neural networks, from which you can choose. Your goal will be to implement those works to address a practical machine learning task.

**MSc Praktikum (Lab) "Statistical Network Analysis"**

Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

6 SWS, 08 140730, biweekly meetings, block session at the end of the semester

In this follow-up lab to our course in winter, you get a chance to address an advanced network analysis problem and to implement recent algorithms and models in statistical network analysis and graph mining.

**MSc eXtAI Lab 1**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

6 SWS, 08 181090

**BSc/MSc Seminar "Data, AI, and Society"**

Dr. Anatol Wegner, Chester Tan

2 SWS, 08 151250, biweekly meetings, block session at the end of the semester

In this seminar, we discuss current societal challenges and opportunities in the application of data science and machine learning. Following an information event at the beginning of the lecture period, the seminar will be organized as a block seminar in the format of a mini-conference. For the final event, students will have to prepare selected works dicussing societal consequences of Big Data and artificial intelligence.

**BSc/MSc Seminar "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes, Franziska Heeg, Lisi Qarkaxhija

2 SWS, 08 151260, biweekly meetings, block session at the end of the semester

In this seminar, we will discuss recent advances in the application of machine learning to graph-structured data. Following an information event at the beginning of the lecture period, we will hold a block seminar in the format of a mini-conference. For this, students will have to prepare selected works on machine learning techniques and applications in data on complex networks.

**Obserseminar (Research Seminar) "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes

2 SWS, 08 153000

**MSc Lecture Statistical Network Analysis**

*I=AKIS-1V / I=AKIS-1Ü*

Prof. Dr. Ingo Scholtes (Lecture), Franziska Heeg, Lisi Qarkaxhija, Chester Tan (Exercises)

2+2 SWS, Wednesday 12-14 (Lecture), Monday 10-12, Thursday 10-12, Friday 10-12 (Exercises)

This course introduces fundamental concepts for the statistical modelling of complex networks and shows how to apply them to practical network analysis tasks. Topics covered include foundations of graph theory, centrality and modularity measures, aggregate statistical characteristics of large networks, random graphs and statistical ensembles of complex networks, generating function analysis of expected graph properties, scale-free networks, stochastic dynamics in networks, spectral analysis, as well as the modelling of time-varying networks. The course material consists of annotated slides for lectures as well as a accompanying git-Repository of jupyter notebooks, which implement and validate the theoretical concepts covered in the lectures. Students can test and deepen their knowledge through weekly exercises. The successful completion of the course requires to pass a final written exam.

**MSc Lecture Introduction to Informatics for Jurists**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner

*10-I=DigL01-222-m01*

2+2 SWS, Thursday 18-20 (Lectures), Exercises upon arragement

This course introduces fundamental concepts of computer science for students in the LL.M. program Digitalization and Law at the Faculty of Law. Introducing both technical aspects of computing, programming, as well as computational and algorithmic thinking, the course covers topics like Algorithms and Data Structures, Introduction to Programming, Encryption, Data Protection and Security, Communication Networks, Internet Technologies, and Cloud Computing. The successful completion of the course requires to pass a final written exam.

**MSc Lab** **Computational Astrophotography**

Prof. Dr. Ingo Scholtes, Prof. Dr. Radu Timofte, Franziska Heeg

*I=PRAK-1P*

6 SWS, Time upon arragement

This lab introduces computational aspects in the photographic imaging of astronomical objects. After a first introduction into astronomical equipment, guiding, and deep sky astrophotography, we will use a computer-controlled telescope and advanced astronomical cameras to collect narrow-band image data on deep sky objects like nebula or galaxies. These imaging sessions will take place outside on campus in the evening, precise dates depend on the weather situation. In a second phase of the lab, students will write python code to address key image processing tasks such as image registration and stacking, debayering of narrow-band data, stretching, and exposure integration. The successful completion of the lab requires to write code and a written report.

**MSc Lab** **Graph Neural Networks**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

*I=PRAK-1P*

6 SWS, Time upon arragement

**eXtAI Lab** **Network Analytics and Visulisation Lab**

*xtAI=L1*

Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

3-6 SWS

**BSc/MSc Seminar Data, AI, and Society**

*I-SEMx-1S*

Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

2 SWS, Time upon arragement

**Oberseminar (Research Seminar) Machine Learning for Complex Networks **

Prof. Dr. Ingo Scholtes

2 SWS, Thursday 12-14

**MSc Lecture "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes

2 SWS, 08 130000, WED 12-14 HS2

This lecture is a direct follow-up of our course "Statistical Network Analysis". In a first chapter we discuss machine learning applications of statistical network models covered in our SNA course. We then turn our attention to state-of-the-art graph representation learning techniques and graph neural networks. Just like for "Statistical Network Analysis", the lectures will integrate practice session in python, in which we demonstrate how to apply the methods. While completing the course Statistical Network Analysis before is certainly beneficial, this course can also be taken independently. A syllabus of the course is available here

**MSc Exercise "Machine Learning for Complex Networks"**

Dr. Anatol Wegner, Franziska Heeg, Lisi Qarkaxhija, Chester Tan

2 SWS, 08 130050, MO 10-12, THU 10-12, FR 10-12

**MSc Praktikum (Lab) "Graph Neural Networks"**

Prof. Dr. Ingo Scholtes, Franziska Heeg

6 SWS, 08 140720, biweekly meetings, block session at the end of the semester

In this lab, you get the chance to take a deep dive into recent machine learning techniques for graph-structured data. We have a collection of interesting recent works on graph neural networks, from which you can choose. Your goal will be to implement those works to address a practical machine learning task.

**MSc Praktikum (Lab) "Statistical Network Analysis"**

Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

6 SWS, 08 140730, biweekly meetings, block session at the end of the semester

In this follow-up lab to our course in winter, you get a chance to address an advanced network analysis problem and to implement recent algorithms and models in statistical network analysis and graph mining.

**MSc eXtAI Lab 1**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

6 SWS, 08 181090

**BSc/MSc Seminar "Data, AI, and Society"**

Dr. Anatol Wegner, Chester Tan

2 SWS, 08 151250, biweekly meetings, block session at the end of the semester

In this seminar, we discuss current societal challenges and opportunities in the application of data science and machine learning. Following an information event at the beginning of the lecture period, the seminar will be organized as a block seminar in the format of a mini-conference. For the final event, students will have to prepare selected works dicussing societal consequences of Big Data and artificial intelligence.

**BSc/MSc Seminar "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes, Franziska Heeg, Lisi Qarkaxhija

2 SWS, 08 151260, biweekly meetings, block session at the end of the semester

In this seminar, we will discuss recent advances in the application of machine learning to graph-structured data. Following an information event at the beginning of the lecture period, we will hold a block seminar in the format of a mini-conference. For this, students will have to prepare selected works on machine learning techniques and applications in data on complex networks.

**Obserseminar (Research Seminar) "Machine Learning for Complex Networks"**

Prof. Dr. Ingo Scholtes

2 SWS, 08 153000

The **teaching language** of all courses above is English. For the labs and seminars, we will hold joint information events in which we introduce possible topics and organisation details. To facilitate your participation, we will hold those information events via Zoom.

The **information event for the two seminars **is scheduled for** Wednesday, April 27, 16:15 - 17:45**

https://uni-wuerzburg.zoom.us/j/66752530071

Meeting-ID: 667 5253 0071

The **information event for the two labs** is scheduled for **Friday, April 29, 12:15 - 13:45**

https://uni-wuerzburg.zoom.us/j/69735178113

Meeting-ID: 697 3517 8113

Please contact us via E-Mail if you would like to participate in a seminar or lab, but cannot participate in the respective information event.

**MSc Lecture Statistical Network Analysis**

Prof. Dr. Ingo Scholtes

2 SWS

**MSc Exercise Statistical Network Analysis**

Prof. Dr. Ingo Scholtes, Dr. Anatol Wegner, Lisi Qarkaxhija, Chester Tan

2 SWS

**eXtAI Lab 1** **Network Analytics and Visulisation Lab**

Prof. Dr. Ingo Scholtes

3 SWS

**Oberseminar (Research Seminar) Machine Learning for Complex Networks **

Prof. Dr. Ingo Scholtes

2 SWS