Hybrid AI – Where data-driven and model-based methods meet

Data-driven machine learning approaches have been very successful the last 10-15 years. At the same time there are many challenges such as how to deal abstract and causal aspects, how to make learning work with significantly less data like humans can do, and how to achieve robust systems which provides formal guarantees and interpretability. Traditional model- or knowledge-based methods are designed to deal with many of these issues, effectively dealing with generality, abstraction, and causality with strong formal guarantees. A current trend in AI and machine learning today is therefore how to combine these different approaches in a principled and effective way. This is often called hybrid AI. During the autumn of 2022 the strategic research environment ELLIIT and Linköping University in Sweden are hosting a 5-week focus period named Hybrid AI – Where data-driven and model-based methods meet. Specific topics are optimisation for learning, learning for optimisation, and statistical-relational approaches to planning, control and decision-making. The main purpose of this topical collection is to encourage publications from interdisciplinary work initiated during this focus period, but other contributions addressing hybrid AI within the intersection between machine learning, optimisation and automatic control are also welcome.



Articles will be displayed here once they are published.