A Galois Framework for the Study of Analogical Classifiers - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

A Galois Framework for the Study of Analogical Classifiers

Miguel Couceiro
Erkko Lehtonen

Abstract

In this paper, we survey some recent advances in the study of analogical classifiers, i.e., classifiers that are compatible with the principle of analogical inference. We will present a Galois framework induced by relation between formal models of analogy and the corresponding classes of analogy preserving functions. The usefulness these general results will be illustrated over Boolean domains, which explicitly present the Galois closed sets of analogical classifiers for different pairs of formal models of Boolean analogies.
Fichier principal
Vignette du fichier
IARML_IJCAI22_Galois4AC (7).pdf (795.89 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03745365 , version 1 (04-08-2022)

Identifiers

  • HAL Id : hal-03745365 , version 1

Cite

Miguel Couceiro, Erkko Lehtonen. A Galois Framework for the Study of Analogical Classifiers. IJCAI-ECAI Workshop on the Interactions between Analogical Reasoning and Machine Learning (IARML@IJCAI-ECAI 2022), Miguel Couceiro; Pierre-Alexandre Murena, Jul 2022, Vienna, Austria. pp.51-61. ⟨hal-03745365⟩
65 View
45 Download

Share

Gmail Facebook X LinkedIn More