An evidential classifier based on Dempster-Shafer theory and deep learning - Archive ouverte HAL Access content directly
Journal Articles Neurocomputing Year : 2021

An evidential classifier based on Dempster-Shafer theory and deep learning

(1) , (1) , (1, 2)
1
2

Abstract

We propose a new classifier based on Dempster-Shafer (DS) theory and a convolutional neural network (CNN) architecture for set-valued classification. In this classifier, called the evidential deep-learning classifier, convolutional and pooling layers first extract highdimensional features from input data. The features are then converted into mass functions and aggregated by Dempster's rule in a DS layer. Finally, an expected utility layer performs set-valued classification based on mass functions. We propose an end-to-end learning strategy for jointly updating the network parameters. Additionally, an approach for selecting partial multi-class acts is proposed. Experiments on image recognition, signal processing, and semantic-relationship classification tasks demonstrate that the proposed combination of deep CNN, DS layer, and expected utility layer makes it possible to improve classification accuracy and to make cautious decisions by assigning confusing patterns to multi-class sets.
Fichier principal
Vignette du fichier
R1_clean_evidential_DL_classifier_0206_TD_PhX.pdf (2.45 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03219203 , version 1 (06-05-2021)

Identifiers

Cite

Zheng Tong, Philippe Xu, Thierry Denoeux. An evidential classifier based on Dempster-Shafer theory and deep learning. Neurocomputing, 2021, 450, pp.275-293. ⟨10.1016/j.neucom.2021.03.066⟩. ⟨hal-03219203⟩
72 View
44 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More