Everyone is talking about AI applications. But the path to a secure AI system with full control of the uncertainties is long and complex. In this lecture you will learn to combine proven model-based system approaches with modern AI methods.

Engineers are trying to develop AI systems by combining knowledge from the areas of neuroscience and cognitive science, applied mathematics, statistics, physics, biology and evolution. This creates a fundamental need for an integrative discipline that brings the different perspectives together and paves the way for the design, analysis and validation of complex, distributed and intelligent systems. In this lecture you will be trained as a future AI system engineer. In particular, you will learn how perspectives of users, modelers, implementers and testers for the design of intelligent systems can be examined. 

With the help of the   Arti  fi  cial Intelligence Systems Engineering Laboratory (AISEL) you try out the    full   AI systems engineering approach in practical projects  :    simulation, bias avoidance, explanatory AI components, optimization of network architectures and transfer of approaches from brain research. 

This lecture largely consists of the processing of practical applications from the areas of mobility and logistics, autonomous driving, driver monitoring systems, video surveillance systems, automated inspection and agriculture that offer high industrial relevance. Teaching content will be made available and processed to accompany the above-mentioned topics.