Using prototypes to improve convolutional networks interpretability - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Using prototypes to improve convolutional networks interpretability

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.

Domains

Neuroscience
Fichier principal
Vignette du fichier
main_NIPS_2017.pdf (207.45 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01651964 , version 1 (29-11-2017)

Identifiers

  • HAL Id : hal-01651964 , version 1

Cite

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⟩
326 View
616 Download

Share

Gmail Facebook X LinkedIn More