Skip to Main content Skip to Navigation
New interface
Conference papers

Vers des classifieurs ontologiquement explicables

Abstract : In order to meet the explainability requirement of AI using Deep Learning (DL), this paper explores the contributions and feasibility of a process designed to create ontologically explainable classifiers while using domain ontologies. The approach is illustrated with the help of the Pizzas ontology that is used to create an image classifier that is able to provide visual explanations concerning a selection of ontological features. The approach is implemented by completing a DL model with ontological tensors that are generated from the ontology expressed in Description Logic.
Complete list of metadata
Contributor : Florent Breuil Connect in order to contact the contributor
Submitted on : Tuesday, June 15, 2021 - 10:00:53 AM
Last modification on : Thursday, November 25, 2021 - 8:22:29 AM
Long-term archiving on: : Thursday, September 16, 2021 - 6:17:15 PM


Files produced by the author(s)


  • HAL Id : emse-03260586, version 1



Grégory Bourguin, Arnaud Lewandowski, Mourad Bouneffa, Adeel Ahmad. Vers des classifieurs ontologiquement explicables. Journées Francophones d'Ingénierie des Connaissances (IC) Plate-Forme Intelligence Artificielle (PFIA'21), Jun 2021, Bordeaux, France. pp 89-97. ⟨emse-03260586⟩



Record views


Files downloads