Artificial Intelligence
(Prof. Stuckenschmidt)
Bachelor Seminar
The Chair of Artificial Intelligence typically offers a Bachelor Seminar in the lecture-free time between HWS and FFS. Participation requires the successful participation in the Elective Course “Künstliche Intelligenz” offered in the HWS term. Candidates will be selected based on the grade achieved in this course. Details of the Seminar will be sent to the participants of the course at the end of the HWS term.
Applications for Bachelor and Master Thesis
The Chair of Artificial Intelligence (Prof. Stuckenschmidt) offers the topics for master thesis that can be found here. Applications should be send to Dr. Ines Rehbein (rehbein@uni-mannheim.de). For bachelor thesis we do not offer such a list. Please directly contact the lecturer/
Artificial Intelligence Research Group
We conduct fundamental and applied research in Artificial Intelligence. We develop AI methods that address the specific challenges of a number of application areas in Industry and Society:
People
Faculty
- Prof. Dr. Heiner Stuckenschmidt Artificial Intelligence
- Dr. Christian Meilicke: Knowledge Representation and Reasoning
Researchers
- Keyvan Amiri Elyasi: Predictive Process Mining with Deep Neural Networks
- Alexander Bubak: Data-Driven Inventory Management
- Patrick Betz: Neuro-Symbolic Integration
- Lea Cohausz: Causal Models and Fair ML in Educational Data Mining
- Thilo Dieing: Social Data Science
- Julia Gastinger: Temporal Graph Mining
- Jakob Kappenberger: Social Simulation and Algorithmic Decision Making
- Ricarda Link: Motion-based Human Activity Recognition
- Konrad Özdemir: Temporal Machine Learning
- Darshit Pandya: Activity Monitoring using Automatic Speech Recognition (ASR) systems
PhD Students
- Julian Aßmann (SAP): Downsizing Large Language Models
- Jannik Brinkmann (InES): Mechanistic Interpretation of Neural Networks
- Christoph Huber (HS Mannheim): Visualization of Smart City Data
- Mareike Keil (em: AG) UI-Design for Neurodivergent Users
- Lukas Kirchdorfer (SAP Signavio): Data-driven Business Process Simulation
- Sascha Marton (InES): Gradient-based Learning of Decision Trees and Forests
- Andreas Meyer-Lindenberg (ZI): Digital Mind Twins
- Simon Ott (Austrian Institute of Technology GmbH): Rule-based Learning for Knowledge Graphs
- Sebastian Paull (AIPERIA): Machine Learning for Master Production Planning
- Florian Rupp (HdM Stuttgart): Fair Game Design with Reinforcement Learning
- Andrej Tschalzev (InES): Deep Learning for Tabular Data
- Nils Wilken (InES): Symbolic Goal Recognition
- Daniel Kerger: Enhancing and understanding public sharing networks
Completed PhDs
- Prof. Dr. Erman Acar (2018): “Knowledge Representation for Automated Decision Making”
- Dr. Taha Alhersh (2021): “From Motion to Human Activity Recognition”
- Dr. Sarah Alturki (2022): “Predicting Student Performance in Interdisciplinary Programs using Methods of Educational Data Mining”.
- Dr. Elena Beisswanger (2013): “Developing Ontological Background Knowledge for Biomedicine”.
- Dr. Fabian Burzlaff (2021): “Knowledge-Driven Architecture Composition”.
- Dr. Alexander Diete (2021): “Towards Multimodal Activity Recognition in Complex Scenarios”
- Dr. Arnab Dutta (2016): “Automated Knowledge Base Extension Using Open Information”.
- Prof. Dr. Kai Eckert (2012): “Usage-driven maintenance of knowledge organization systems”.
- Dr. Daniel Fleischhacker (2016): “Detecting Errors in Linked Data Using Ontology Learning and Outlier Detection”.
- Dr. Oliver Frendo (2021): “Improving Smart Charging for Electric Vehicle Fleets by Integrating Battery and Prediction Models”.
- Dr. David Friede (2023): “Exploring discrete representations in stochastic computation graphs Challenges, benefits, and novel strategies”.
- Dr. Rim Helaoui* (2016): “On Leveraging Statistical and Relational Information for the Representation and Recognition of Complex Human Activities”.
- Dr. Jakob Huber* (2019): “Data-driven Decision Support for Perishable Goods”.
- Dr. Jonathan Kobbe (2023): “Automatic generation of structured explanations for arguments from consequences”.
- Dr. Elena Kuss (2019): “Evaluation of Process Model Matching Techniques”.
- Dr. Sascha Marton* (2025): “Learning Tree-based Models with Gradient Descent”
- Dr. Christian Meilicke* (2011): “Alignment Incoherence in Ontology Matching”.
- Dr. Jan Noessner* (2014): “Efficient Maximum A-Posteriori Inference in Markov Logic and Application in Description Logics”.
- Dr. Andreas Nolle (2021): “Federated Knowledge Base Debugging in DL-LiteA".
- Dr. Michael Oesterle (2024) “Self-learning restriction-based governance of multi-agent systems”.
- Dr. Christoph Pinkel (2016): “Incremental, Interactive,Inter-Model Mapping Generation”.
- Dr. Bernhard Schäfer* (2023): “Recognizing Hand-drawn Diagrams in Images”
- Dr. Anne Schlicht* (2012): “Scaling Up Description Logic Reasoning by Distributed Resolution”.
- Dr. Jörg Schönfisch (2018): “Scalable Handling of Uncertain Data and Knowledge Graphs”
- Dr. Diana Sola (2023): “Recommending activities for business process model”.
- Dr. Timo Sztyler* (2019): “Sensor-based human activity recognition: Overcoming issues in a real world setting”
- Dr. Christoph Theil (2022): “Uncertainty, Risk, and Financial Disclosures -
Applications of Natural Language Processing in Behavioral Economics”. - Dr. Caecilia Zirn (2016): “Fine-grained Position Analysis for Political Texts”.
* With Distinction
Former Members still active in Science
- Erman Acar – Assistant Professor in Explainable AI for Finance – University of Amsterdam
- Sarah Alturki – Assistant Professor Princess Nourah Bint Abdulrahman University, Rihyad, Saudi Arabia
- Christian Bartelt – Professor for Methods and Applications of Machine Learning at TU Clasuthal.
- Melisachew Wudage Chekol – Assistant Professor for Data Management at the Utrecht University
- Kai Eckert – Professor at University of Applied Science Mannheim
- Ioana Hulpus – Assistant Professor at Utrecht University
- Rim Helaoui – Director Data & AI Innovation & Strategy at Philips Research Eindhoven
- Elena Kuss – Professor for Business Informatics Reuthlingen University of Applied Science
- Goran Glavas – Professor for Natural Language Processing at Würzburg University
- Stefan Lüdtke – Tenure Track Assistant Professor for Marine Data Science at University of Rostock
- Federico Nanni - Research Data Scientist at the Allan Turing Institute London
- Mathias Niepert – Professor for Machine Learning and Simulation at Stuttgart University
- Sanja Stajner – Senior Research Scientist at Symanto.
- Timo Sztyler – Research Scientist at NEC Labs Europe Heidelberg
Projects
Projects
- NEST-bw: Netzwerk zu Verfahren der Studienorientierung und Selbstreflexion (2024 – )
- Meeting KI: Entwicklung eines intelligenten Meeting- Unterstützungsystems (2024 – 2026)
- TransforMA: Technologie- und Wissenstransfer für die aktive Gestaltung von Transformationsprozessen (2023 – 2027)
- sMArt roots – Smart City Modellstadt Mannheim (2021 – 2026)
- CAIUS: Consequences of AI Applications on Urban Societies (2019 – 2025)
- KISync – AI for integrated supply chain optimization (2022 – 2025)
Software and Data
- Activity Recognition Data and Algorithms
- AnyBURL (A state of the art rule learner for Knowledge-Base Completion)
- ALCOMO (a tool for repairing ontology alignments)
- Rockit (a query engine for Markov Logic)
- ELOG (a reasoner for log-linear description logics.
Courses FSS
Industrial Applications of Artificial Intelligence – Lecture (Lecture, english)
Course type:
Lecture
ECTS:
6
Course suitable for:
Language of instruction:
english
Credit hours 1:
2
Attendance:
On-campus and online, live & recorded
Learning target:
Expertise:
Students will acquire knowledge about possible applications of machine learning in different branches of industry as well as the dominant methods used in these areas:
Methodological competence:
Successful participants will be able to: Identify potential for applying AI methods in different areas of industry; Decide on a suitable method for addressing typical problems in these industries
Personal competence:
Participants will learn to reflect and document their own learning process
Students will acquire knowledge about possible applications of machine learning in different branches of industry as well as the dominant methods used in these areas:
- Primary Sector: Agriculture, Energy Production
- Secondary Sector: Production, Supply Chain Management
- Tertiary Sector: Healthcare, Education, Finance
Methodological competence:
Successful participants will be able to: Identify potential for applying AI methods in different areas of industry; Decide on a suitable method for addressing typical problems in these industries
Personal competence:
Participants will learn to reflect and document their own learning process
Recommended requirement:
Literature:
Various Scientific Publications – details in the lecture slides
Examination achievement:
Submission of a Learning Portfolio
Instructor(s):
Prof. Dr. Heiner Stuckenschmidt
Description:
Participants will learn about the use of Artificial Intelligence methods, mostly from the field of machine learning in different sectors and industries. They will learn about application areas in the primary, secondary and tertiary sector, get an introduction to examples of such applications that have been published on a scientific level and gather some experience in working with data from the respective fields using publically available datasets.
More information
1 Credit hours indicate the duration of a course which is offered weekly during one semester. One credit hour equals 45 minutes.
Wirtschaftsinformatik II: Grundlagen der Modellierung (Lecture, german)
Course type:
Lecture
ECTS:
6.0
Course suitable for:
Bachelor, Master
Language of instruction:
german
Credit hours 1:
2
Attendance:
On-campus and online, live
Learning target:
Fachkompetenz:
Methodenkompetenz:
Personale Kompetenz:
- Kenntnisse aktueller Modellierungssprachen und Werkzeugen.
- Verständnis für Grundprinzipien und Formalen Grundlagen der Modellierung von Anwendungsdomänen und Prozessen.
Methodenkompetenz:
- Beschreibung von Domänen und Prozesse einfacher und mittlerer Komplexität mit Hilfe gängiger Sprachen und Werkzeuge
Personale Kompetenz:
- Verständnis komplexer Zusammenhänge, Arbeiten im Team, Kommunikation von Modellierungsentscheidungen
Recommended requirement:
Examination achievement:
Studienbeginn ab HWS 2011:
Erfolgreiche Teilnahme am Übungsbetrieb
Schriftliche Klausur (90 Minuten)
Erfolgreiche Teilnahme am Übungsbetrieb
Schriftliche Klausur (90 Minuten)
Studienbeginn vor HWS 2011:
Schriftliche Klausur (90 Minuten)
Instructor(s):
Prof. Dr. Heiner Stuckenschmidt, Dr. Christian Meilicke
Description:
Die Vorlesung behandelt die Rolle konzeptueller Modellierung in der Wirtschaftsinformatik. Es werden Vorteile und Grenzen der Modlelierung im Unternehmenkontext aufgezeigt und Modellierungssprachen und Werkzeuge eingeführt. Inhalte der Veranstaltung umfassen unter anderem:
- Modellierungsprinzipien
- Praxisnahe Sprachen (UML, BPMN)
- Formale Grundlagen von Modellierungssprachen (Logik, Pertri-Netze)
- Modellierungswerkzeuge.
More information
1 Credit hours indicate the duration of a course which is offered weekly during one semester. One credit hour equals 45 minutes.
Courses HWS
Data Science in Action (ENGAGE.EU Signature Course) (Lecture, english)
Course type:
Lecture
ECTS:
6.0
Course suitable for:
Language of instruction:
english
Credit hours 1:
2
Attendance:
Online, live
Recommended requirement:
Literature:
Recommended Papers from invited speakers
Examination achievement:
Written Essay
Instructor(s):
Prof. Dr. Heiner Stuckenschmidt
Description:
The Mannheim Center for Data Science (MCDS) offers a lecture series on “Data Science in Action” together with the European University ENGAGE.EU (Signature Course). Renowned researchers from the University of Mannheim and its partner universities Université Toulouse Capitole, Tilburg University, Hanken School of Economics, Norwegian School of Economics (NHH) and WU Vienna University of Economics and Business will provide insights into their data-based research. The speakers represent various disciplines, including business administration, computer science, political science, business education, media and communication studies, sociology, psychology and linguistics. The lecture series thus represents the relevance of data science in its entire breadth for science and society.
More information
1 Credit hours indicate the duration of a course which is offered weekly during one semester. One credit hour equals 45 minutes.
Decision Support (Lecture, english)
Course type:
Lecture
ECTS:
6.0
Course suitable for:
Bachelor, Master
Language of instruction:
english
Credit hours 1:
2
Attendance:
Live & on-campus
Learning target:
Expertise:
Students will acquire basic knowledge of the techniques, opportunities and applications of decision theory.
Methodological competence:
Students will acquire basic knowledge of the techniques, opportunities and applications of decision theory.
Methodological competence:
- Successful participants will be able to identify opportunities for decision support in an enterprise environment, select and apply appropriate techniques, and interpret the results.
- project presentation skills
Personal competence:
- team work skills
- presentation skills
Recommended requirement:
Examination achievement:
Written examination (90 minutes), homework assignments, case studies
Instructor(s):
Lea Cohausz, Prof. Dr. Heiner Stuckenschmidt
Description:
The course provides an introduction to decision support techniques as a basis for the design of decision support systems. The course will cover the following topics:
- Decision Theory
- Decision- and Business Rules
- Planning Methods and Algorithms
- Probabilistic Graphical Models
- Game Theory and Mechanism Design
More information
1 Credit hours indicate the duration of a course which is offered weekly during one semester. One credit hour equals 45 minutes.
Decision Support (Lecture, english)
Course type:
Lecture
ECTS:
6.0
Course suitable for:
Bachelor, Master
Language of instruction:
english
Credit hours 1:
1
Attendance:
Live & on-campus
Learning target:
Expertise:
Students will acquire basic knowledge of the techniques, opportunities and applications of decision theory.
Methodological competence:
Students will acquire basic knowledge of the techniques, opportunities and applications of decision theory.
Methodological competence:
- Successful participants will be able to identify opportunities for decision support in an enterprise environment, select and apply appropriate techniques, and interpret the results.
- project presentation skills
Personal competence:
- team work skills
- presentation skills
Recommended requirement:
Examination achievement:
Written examination (90 minutes), homework assignments, case studies
Instructor(s):
Lea Cohausz, Prof. Dr. Heiner Stuckenschmidt
Description:
The course provides an introduction to decision support techniques as a basis for the design of decision support systems. The course will cover the following topics:
- Decision Theory
- Decision- and Business Rules
- Planning Methods and Algorithms
- Probabilistic Graphical Models
- Game Theory and Mechanism Design
More information
1 Credit hours indicate the duration of a course which is offered weekly during one semester. One credit hour equals 45 minutes.
Decision Support (Lecture, english)
Course type:
Lecture
ECTS:
6.0
Course suitable for:
Bachelor, Master
Language of instruction:
english
Credit hours 1:
2
Attendance:
Live & on-campus
Learning target:
Expertise:
Students will acquire basic knowledge of the techniques, opportunities and applications of decision theory.
Methodological competence:
Students will acquire basic knowledge of the techniques, opportunities and applications of decision theory.
Methodological competence:
- Successful participants will be able to identify opportunities for decision support in an enterprise environment, select and apply appropriate techniques, and interpret the results.
- project presentation skills
Personal competence:
- team work skills
- presentation skills
Recommended requirement:
Examination achievement:
Written examination (90 minutes), homework assignments, case studies
Instructor(s):
Lea Cohausz, Prof. Dr. Heiner Stuckenschmidt
Description:
The course provides an introduction to decision support techniques as a basis for the design of decision support systems. The course will cover the following topics:
- Decision Theory
- Decision- and Business Rules
- Planning Methods and Algorithms
- Probabilistic Graphical Models
- Game Theory and Mechanism Design
More information
1 Credit hours indicate the duration of a course which is offered weekly during one semester. One credit hour equals 45 minutes.
Artificial Intelligence (Lecture, german)
Course type:
Lecture
ECTS:
6.0
Course suitable for:
Bachelor
Language of instruction:
german
Credit hours 1:
4
Attendance:
Live & on-campus
Learning target:
Fachkompetenz:
Ziele und Grundlagen der Künstlichen Intelligenz. Suchverfahren als universelle Problemlösungsverfahren. Problemkomplexität und Heuristische Lösungen. Eigenschaften und Zusammenhang zwischen unterschiedlichen Suchverfahren.
Methodenkompetenz:
Beschreibung konkreter Aufgaben als Such-, Constraint- oder Planungsproblem. Implementierung unterschiedlicher Suchverfahren und Heuristiken.
Ziele und Grundlagen der Künstlichen Intelligenz. Suchverfahren als universelle Problemlösungsverfahren. Problemkomplexität und Heuristische Lösungen. Eigenschaften und Zusammenhang zwischen unterschiedlichen Suchverfahren.
Methodenkompetenz:
Beschreibung konkreter Aufgaben als Such-, Constraint- oder Planungsproblem. Implementierung unterschiedlicher Suchverfahren und Heuristiken.
Recommended requirement:
Examination achievement:
Erfolgreiche Teilnahme am Übungsbetrieb
schriftliche Klausur (90 Minuten)
schriftliche Klausur (90 Minuten)
Instructor(s):
Dr. Christian Meilicke
Description:
- Problemeigenschaften und Problemtypen
- Problemlösen als Suche, Anwendung im Bereich Computerspiele
- Constraintprobleme und deren Lösung
- Logische Constraints
More information
1 Credit hours indicate the duration of a course which is offered weekly during one semester. One credit hour equals 45 minutes.