Our NFDI4DS Lecture Series continues with Lecture 6 on 26. Nov 2024 9:00 online.
This lecture will be in cooperation with the NFDI Section Infra WG DS&AI.
Title: Safety of AI Systems with Executable Causal Models and Statistical Data Science
AI systems that learn from data present a unique challenge for safety, as there is no specific design artifact, model, or code to analyse and verify. The safety assurance challenges become even more complex in cooperative intelligent systems, like collaborative robots and autonomous vehicles. These systems are often loosely interconnected, allowing them to form and dissolve configurations dynamically. Evaluating the consequences of failures in largely unpredictable configurations is a daunting task. Intentional or unintentional interactions between systems, along with newly learned behaviours and varying environmental conditions, can lead to unpredictable or emergent behaviours. Achieving complete safety assurance of such systems of systems at the design stage through traditional model-based methods is unfeasible. In this talk, I will explore these challenges and introduce executable causal models and statistical techniques that may help address these emerging issues.
Speaker: Yiannis Papadopoulos
Professor Papadopoulos is a foremost international expert on safety of computer systems including safety of AI and intelligent systems. He is leading a research group on Dependable Intelligent Systems and has pioneered a method and set of tools for model-based safety and reliability assessment and evolutionary optimisation of complex engineering systems known as Hierarchically Performed Hazard Origin and Propagation Studies.
Professor Papadopoulos is currently developing new model-based and data driven technologies for dynamic safety assurance of autonomous and cooperative systems that include swarms of robots and autonomous cars using cutting-edge statistical methods for improving the safety of AI, including safety of Machine Learning, Deep Learning and Large Language Models.
Registration: Please register via https://events.hifis.net/event/1926