The Mathematics of Comparing Objects
Marcus Weber, Konstantin Fackeldey
TL;DR
This paper examines the mathematical foundations of comparing objects, using a crime story analogy to explore the assumptions under which AI conclusions about police success are realistic.
Contribution
It introduces a formal framework for analyzing the validity of AI conclusions in object comparison scenarios based on probabilistic assumptions.
Findings
Identifies key assumptions for AI to reliably compare objects
Provides mathematical criteria for the realism of AI conclusions
Highlights limitations of AI in crime story analogy
Abstract
"After reading two different crime stories, an artificial intelligence concludes that in both stories the police has found the murderer just by random." -- To what extend and under which assumptions this is a description of a realistic scenario?
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsData Mining Algorithms and Applications · Computability, Logic, AI Algorithms · Rough Sets and Fuzzy Logic