Editing Boolean Classifiers: A Belief Change Perspective

Authors

  • Nicolas Schwind National Institute of Advanced Industrial Science and Technology, Tokyo, Japan
  • Katsumi Inoue National Institute of Informatics, Tokyo, Japan The Graduate University for Advanced Studies, SOKENDAI, Tokyo, Japan
  • Pierre Marquis Univ. Artois, CNRS, CRIL, F-62300 Lens, France Institut Universitaire de France

DOI:

https://doi.org/10.1609/aaai.v37i5.25801

Keywords:

KRR: Belief Change

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.
AAAI-23 Proceedings Cover

Downloads

Published

2023-06-26

How to Cite

Schwind, N., Inoue, K., & Marquis, P. (2023). Editing Boolean Classifiers: A Belief Change Perspective. Proceedings of the AAAI Conference on Artificial Intelligence, 37(5), 6516-6524. https://doi.org/10.1609/aaai.v37i5.25801

Issue

Vol. 37 No. 5: AAAI-23 Technical Tracks 5

Section

AAAI Technical Track on Knowledge Representation and Reasoning