Human-Centered Artificial Intelligence

Wendy E. Mackay (1) , John Shawe-Taylor (2) , Frank van Harmelen (3)

1 EX-SITU - Extreme Situated Interaction - LISN
2 UCL - University College of London [London]
3 UvA - University of Amsterdam [Amsterdam] = Universiteit van Amsterdam

This report documents the program and the outcomes of Dagstuhl Perspectives Workshop 22262 "Human-Centered Artificial Intelligence". The goal of this Dagstuhl Perspectives Workshops is to provide the scientific and technological foundations for designing and deploying hybrid human-centered AI systems that work in partnership with human beings and that enhance human capabilities rather than replace human intelligence. Fundamentally new solutions are needed for core research problems in AI and human-computer interaction (HCI), especially to help people understand actions recommended or performed by AI systems and to facilitate meaningful interaction between humans and AI systems. Specific challenges include: learning complex world models; building effective and explainable machine learning systems; developing human-controllable intelligent systems; adapting AI systems to dynamic, open-ended real-world environments (in particular robots and autonomous systems); achieving in-depth understanding of humans and complex social contexts; and enabling self-reflection within AI systems.

Mots clés: Human-centered Artificial Intelligence; Human-Computer Interaction; Hybrid Intelligence

Domaines: Informatique [cs]

Wendy E. Mackay, John Shawe-Taylor, Frank van Harmelen. Human-Centered Artificial Intelligence. Dagstuhl Reports, Vol. 12, Issue 6. 2023, pp.112-117. ⟨hal-04440376⟩