At this year's AI Safety Workshop, which will take place virtually on August 19 and 20, 2021, the Fraunhofer Institute for Cognitive Systems IKS will be represented with three research contributions. In addition to a paper presentation on the robustness of AI models and a poster pitch on Reinforcement Learning, the second day of the event will be opened by a keynote by Prof. Dr. Simon Burton on the topic of safety assurance.
The workshops seeks to explore new ideas on safety engineering and puts the focus on strategic, ethical and policy aspects of safety-critical AI-based systems .Due to the current situation the workshop will take place virtually.
»Domain Shifts in Reinforcement Learning: Identifying Disturbances in Enviroments«
- 19th August 2021, 1:45 PM
- Poster Pitch
- Tom Haider, Felippe Schmoeller Roza, Dirk Eilers, Karsten Roscher, Stephan Günnemann
- Poster
- Poster paper
»Measuring Ensemble Diversity and Its Effects on Model Robustness«
- 19th August 2021, 3:20 PM
- Paper Presentation
- Lena Heidemann, Adrian Schweiger, Karsten Roscher
- Paper
»Safety, Complexity, AI and Automated Driving – Holistic Perspectives on Safety Assurance«
- 20th August 2021, 12:00 PM
- Keynote
- Prof. Dr. Simon Burton