Paper[edit]

Paper
edit
description	scientific paper published in CEUR-WS Volume 3197
id	Vol-3197/invited2
wikidataid	Q117341777→Q117341777
title	Rectifying Classifiers
pdfUrl	https://ceur-ws.org/Vol-3197/invited2.pdf
dblpUrl	https://dblp.org/rec/conf/nmr/Marquis22
volume	Vol-3197→Vol-3197
session	→

Rectifying Classifiers[edit]

Rectifying Classifiers
Pierre Marquis
Univ. Artois, CNRS, CRIL / Institut Universitaire de France, France




1. Abstract
Dealing with high-risk or safety-critical applications calls for the development of trustworthy AI
systems. Beyond prediction, such systems must offer a number of additional facilities, including
explanation and verification.
   The case when the prediction made is deemed wrong by an expert calls for still another
operation, called rectification. Rectifying a classifier aims to guarantee that the predictions
made by the classifier (once rectified) comply with the expert knowledge. Here, the expert is
supposed more reliable than the predictor, but their knowledge is typically incomplete.
   Focusing on Boolean classifiers, I will present rectification as a change operation. Following an
axiomatic approach, I will give some postulates that must be satisfied by rectification operators.
I will show that the family of rectification operators is disjoint from the family of revision
operators and from the family of update operators. I will also present a few results about the
computation of a rectification operation.




NMR 2022: 20th International Workshop on Non-Monotonic Reasoning, August 07–09, 2022, Haifa, Israel
" marquis@cril.univ-artois.fr (P. Marquis)
~ http://www.cril.univ-artois.fr/~marquis/ (P. Marquis)
� 0000-0002-7979-6608 (P. Marquis)
                                    © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
 CEUR
 Workshop
 Proceedings
               http://ceur-ws.org
               ISSN 1613-0073
                                    CEUR Workshop Proceedings (CEUR-WS.org)




                                                                                                        2
�

Rectifying Classifiers[edit]

Rectifying Classifiers
Pierre Marquis
Univ. Artois, CNRS, CRIL / Institut Universitaire de France, France




1. Abstract
Dealing with high-risk or safety-critical applications calls for the development of trustworthy AI
systems. Beyond prediction, such systems must offer a number of additional facilities, including
explanation and verification.
   The case when the prediction made is deemed wrong by an expert calls for still another
operation, called rectification. Rectifying a classifier aims to guarantee that the predictions
made by the classifier (once rectified) comply with the expert knowledge. Here, the expert is
supposed more reliable than the predictor, but their knowledge is typically incomplete.
   Focusing on Boolean classifiers, I will present rectification as a change operation. Following an
axiomatic approach, I will give some postulates that must be satisfied by rectification operators.
I will show that the family of rectification operators is disjoint from the family of revision
operators and from the family of update operators. I will also present a few results about the
computation of a rectification operation.




NMR 2022: 20th International Workshop on Non-Monotonic Reasoning, August 07–09, 2022, Haifa, Israel
" marquis@cril.univ-artois.fr (P. Marquis)
~ http://www.cril.univ-artois.fr/~marquis/ (P. Marquis)
� 0000-0002-7979-6608 (P. Marquis)
                                    © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
 CEUR
 Workshop
 Proceedings
               http://ceur-ws.org
               ISSN 1613-0073
                                    CEUR Workshop Proceedings (CEUR-WS.org)




                                                                                                        2
�