The module "Responsible Artificial Intelligence" aims to convey the methodological basics for a transparent, fair and responsible use of AI models. The module consists of two lectures, one taught in WiSe 23/24 and one taught in SoSe 24.
The focus of the lecture "Responsible Artificial Intelligence 1" taught in WiSe 23/24 will be on explanation methods, i.e. techniques that act as a bridge between humans and black box AI by making the AI's functionality and the basis for its predictions transparent. This course will cover different types of explanation methods and discuss their advantages and disadvantages as well as their theoretical foundations.
- Trainer/in: Wojciech Samek