Explaining the Uncertainty in AI-Assisted Decision Making
نویسندگان
چکیده
The aim of this project is to improve human decision-making using explainability; specifically, how explain the (un)certainty machine learning models. Prior research has used uncertainty measures promote trust and decision-making. However, direction explaining why AI prediction confident (or not confident) in its needs be addressed. By model uncertainty, we can trust, understanding for users.
منابع مشابه
Decision Making under Uncertainty: Operations Research Meets AI (Again)
Models for sequential decision making under uncertainty (e.g., Markov decision processes,or MDPs) have been studied in operations research for decades. The recent incorporation of ideas from many areas of AI, including planning, probabilistic modeling, machine learning, and knowledge representation) have made these models much more widely applicable. I briefly survey recent advances within AI i...
متن کاملDecision Making with Uncertainty
In this paper we discuss decision making based on incomplete knowledge. Asthe results of our decisions have always some uncertainties in these cases, we developeda method to measure the advantages brought by those possible solutions of our problem,which makes our decision making problem easier. Our proposal is entirely formulizedwithin the so called classical two valued logic, so it has a solid...
متن کاملDecision making under uncertainty
1 Laboratory of Computational Neuroscience, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland 2 Laboratoire de Recherché en Neuroimagerie, Le Centre Hospitalier Universitaire Vaudois, Lausanne, Switzerland 3 Information Processing and Economic Decision Making, Department of Psychology, Universität Konstanz, Konstanz, Germany 4 Economic Psychology, Department of Psychology, Univers...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i13.26920