Skip to Main content Skip to Navigation
Conference papers

Using prototypes to improve convolutional networks interpretability

Thalita F Drumond 1, 2, 3 Thierry Viéville 1, 2, 3 Frédéric Alexandre 1, 2, 3 
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : We propose a method that allows the interpretation of the data representation obtained by CNN, through introducing prototypes in the feature space, that are later classified into a certain category. This way we can see how the feature space is structured in link with the categories and the related task.
Document type :
Conference papers
Complete list of metadata

Cited literature [23 references]  Display  Hide  Download
Contributor : Thierry Viéville Connect in order to contact the contributor
Submitted on : Wednesday, November 29, 2017 - 5:32:58 PM
Last modification on : Monday, July 25, 2022 - 3:44:22 AM


Files produced by the author(s)


  • HAL Id : hal-01651964, version 1


Thalita F Drumond, Thierry Viéville, Frédéric Alexandre. Using prototypes to improve convolutional networks interpretability. NIPS 2017 - 31st Annual Conference on Neural Information Processing Systems: Transparent and interpretable machine learning in safety critical environments Workshop, Dec 2017, Long Beach, United States. ⟨hal-01651964⟩



Record views


Files downloads