[4L5-GS-1b] Fundamental AI, theory algorithm

4:00 PM - 4:15 PM JST(7:00 AM - 7:15 AM UTC)

[4L5-GS-1b-03] Iterated Belief Change as Learning

〇Nicolas Schwind¹, Katsumi Inoue², Sébastien Konieczny³, Pierre Marquis^3,4 (1. National Institute of Advanced Industrial Science and Technology (AIST), 2. National Institute of Informatics, 3. Univ. Artois, CNRS, CRIL, Lens, France, 4. Institut Universitaire de France)

Keywords:

Knowledge Representation and Reasoning,Iterated Belief Change,Machine Learning,Binary Classification

In this work, we show how the class of improvement operators -- a general class of iterated belief change operators -- can be used to define a learning model. Focusing on binary classification, we present learning and inference algorithms suited to this learning model and we evaluate them empirically. Our findings highlight two key insights: first, that iterated belief change can be viewed as an effective form of online learning, and second, that the well-established axiomatic foundations of belief change operators offer a promising avenue for the axiomatic study of classification tasks.