- Introduction to Business Process Management: Based on the "method kit" of Computational Intelligence business processes will be modeled and optimised in this course (Koordination as individual decision).
- Introduction to Computational Intelligence: For many assignment and permutation problems an exponential growth of the number of solutions prohibits the application of optimization algorithms known from Operations Research. Rather, literature and practitioners resort to the application of heuristics. Heuristics come with much lower computational effort but as a downside - cannot provide a guarantee for the optimality of the solutions found. First, the course focuses on local search heuristics inspired by analogies to nature (Genetic Algorithms and Simulated Annealing) and Tabu Search and compares their applicability for different classes of planning problems. Furthermore, most decision processes do not only confront us with a high number of alternatives but also with uncertainty. We will show how Machine Learning (esp. Reinforcement Learning) can address this uncertainty in complex decision processes, when an appropriate representation of the search space and the value functions can be found. Artificial Neural Networks are introduced (as another paradigm in analogy to nature) as a computational solution of this representational problem.
- Optimization of Logistics Systems (OLS): The course is aimed at providing an overview of the quantitative methods that can be used to support the optimal design and management of modern logistics systems. Special attention will be devoted to the demand analysis and data procurement, to the design of logistic networks and to the optimization of long distance and local transportation of freights. Illustrative examples of models and algorithms will be treated by using general purpose and special solvers.
- Electronic Markets: Information Systems for Electronic Markets: The focus of this course - offered in common with the chairs Marketing, VWL I and Private Law, Economic Law, Intellectual Property - is on modeling and optimising interplant processes using modern IT networking.
- Introduction to Multi-Agent Systems: Multi-Agent Systems allow the modeling of interacting processes between autonomous acting individuals in distributed systems while using compact software modules for deployment. On the one hand due to their modularity MAS are very appropriate for the control of inter-enterprise processes that are common in logistics and supply chain management, on the other hand MAS are suitable for the micro-simulation of socio-technical and economic processes. The MAS lecture provides an introduction into the technical foundations of MAS, like e.g. ontologies and FIPA system architecture and additionally discusses aspects of model design and implementation. In this context the economically and game-theoretically oriented domain of mechanism design is treated jointly with associated aspects like trust and reputation. In its final part the lecture is mainly concerned with the deployment of MAS technologies in the domain of logistics, supply chain and IT-resource management in practice.
- Standard Software in Process Management: The block course "Standard Business Software in Process Management" demonstrates the implementation of operational processes in standard software by means of case studies. Starting points are the models and optimization approaches exemplified in "Business Process Management".
- Multivariate and Nonlinear Models:Analysis and Learning of (non)linear Relations from Data
Multivariate Linear Models
- Data Analysis and Graphical Presentation
- Models for multivariate data analysis,
- Principal Component Analysis and Cluster Analysis
Multivariate Nonlinear Models
- Data Analysis and Graphical Presentation
- Artificial Neural Networks
- Kernel-based Estimators and Support Vector Machines
The lecture provides an overview of problems and state-of-the-art techniques of generalizing models from (small or large) data sets with known or unknown hypotheses regarding the underlying functional dependencies. Data sets from various application domains are analyzed and appropriate software tools introduced.
* In Master Program the module chosen in Bachelor program cannot be selected once again.