2023 AAAI AAAI 2023

Editing Boolean Classifiers: A Belief Change Perspective

Abstract

Abstract This paper is about editing Boolean classifiers, i.e., determining how a Boolean classifier should be modified when new pieces of evidence must be incorporated. Our main goal is to delineate what are the rational ways of making such edits. This goes through a number of rationality postulates inspired from those considered so far for belief revision. We give a representation theorem and present some families of edit operators satisfying the postulates.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
🧭 Keyword Pioneer — boolean classifier
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Deep Learning, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing