Lehre
Die Lehre des Lehrstuhls beschäftigt sich mit Kompetenzen, wie sie in der Praxis von Data Scientists, Machine Learning Engineers und Entscheidern an der Schnittstelle Management und Informationstechnologie benötigt werden. Diese umfasst sowohl Fertigkeiten im Umgang mit Methoden und Verfahren der künstlichen Intelligenz, als auch in der Gestaltung vollständiger Datenanalysepipelines, inkl. Tools und IT-Infrastruktur. Darüber hinaus setzt der Lehrstuhl Schwerpunkte auf Methoden und Verfahren aus den Bereichen Smart Cities, Energie und Mobilität - beispielsweise auf Verfahren zur Analyse räumlicher Daten.
Die Philosophie der Lehre des Lehrstuhls ist es, Studierende in die Lage zu versetzen, komplexe Probleme eigenständig zu lösen. Dafür strebt der Lehrstuhl grundsätzlich eine formale Ausbildung an, um die Studierenden beim Aufbau wiederverwendbarer methodischer und anwendungsorientierter Kompetenzen zu unterstützen.
Welche Vorlesungen jeweils im Sommer- und Wintersemester angeboten werden entnehmen Sie bitte dem Menü. Des Weiteren bietet der Lehrstuhl verschiedene Seminare für Bachelor- und Masterstudenten an.
Wintersemester
Level: Master
Scope: 4 SWS / 5 ECTS
Links: WueStudy
The course is read in collaboration with the Chair of Information Systems and Business Analytics.
Learning Objectives
- Getting to know the principles and frameworks in the research field of Data Science,
presentation of numerous application examples - Design, implementation and evaluation of the most important algorithms within an end-to-end workflow in the field of Data Science (including import of the data, their analysis and their processing)
- Application of Jupyter notebooks and their infrastructure (collection, storage, retrieval and analysis of data)
- Understanding of a data-based & analytical approach to decision-making problems
Providing knowledge for the implementation and execution of solutions in the field of business analytics
Agenda
- Introduction
- Descriptive Analytics
- Recap: Machine Learning
- Feature Engineering
- Deep Learning for Tabular Data
- Deep Learning for Image Classification
- From Data to Production
- Natural Language Processing with Huggingface
- Guest lecture snapADDY
- Project work
Organization
Learning Materials on WueCampus:
- Jupyter Notebooks
- Datasets and exercises
- Uploaded solution template
Exam: Final group project
Sommersemester
Level: Bachelor
Scope: Lecture (2 SWS) and exercise session (2 SWS) / 5 ECTS
Links: WueStudy
Learning Objectives
In this course, you will learn the concepts and terminology of simulation, as well as how to create and analyze simulation models using a simulation software package. You will also learn how to design and conduct simulation experiments, and how to validate and verify simulation models.
You will gain a solid foundation in probability and statistical analysis, which is essential for understanding and analyzing simulation results. You will also have the opportunity to explore a range of simulation applications in various fields, such as engineering, operations research, finance, and healthcare.
In addition, you will have the chance to apply these techniques to real-world problems through case studies.
Agenda
- Introduction to simulation: concepts, terminology, and applications.
- Probability and statistical analysis: probability distributions, random variables, statistical tests, and confidence intervals.
- Design of experiments: principles of experimental design, design of simulation experiments, analyzing simulation results.
- Validation and verification: techniques for validating and verifying simulation models, sensitivity analysis, and model robustness.
- Applications of simulation: examples of simulation applications in various fields, such as engineering, operations research, finance, and healthcare.
- Case studies: application of simulation techniques to real-world problems.
- Simulation software: overview of simulation software packages and their features, hands-on experience with a simulation software package.
Organization
Learning Materials on WueCampus:
- Lecture Slides
- Datasets and exercises
Exam: Final written exam
Level: Master
Scope: Lecture (2 SWS) and exercise session (2 SWS) / 5 ECTS
Links: WueStudy
Learning Objectives
In this course, you will learn
- the fundamentals for developing, deploying and maintaining machine learning systems in companies (MLOps),
- to design the associated IT infrastructure,
- to manage machine learning projects in organizations, including staffing and the choosing an appropiate organizational form.
You will refine and test your skills by practicing the theoretical concepts during exercise sessions. This practice will prepare you for the final project, where you and your peers will develop your own Machine Learning System.
Agenda
- Introduction to Enterprise AI
- Business Requirements for AI Systems
- ML Ops I: Data Engineering
- ML Ops II: Obtaining Training Data
- ML Ops III: Data Preprocessing
- ML Ops IV: Feature Engineering
- ML Ops V: Modeling & Evaluation
- ML Ops VI: Deployment
- ML Ops VII: System Monitoring
- ML Ops VIII: Updating in Production
- Guest Lecture
- Instrastructure and Tools
- Managing Machine Learning Teams
Organization
Learning Materials on WueCampus:
- Lecture Slides
- Datasets and exercises
- Uploaded solution template
Exam: Final group project
