Logistic regression revisited: belief function analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Logistic regression revisited: belief function analysis

Résumé

We show that the weighted sum and softmax operations performed in logistic regression classifiers can be interpreted in terms of evidence aggregation using Dempster's rule of combination. From that perspective, the output probabilities from such classifiers can be seen as normalized plausibilities, for some mass functions that can be laid bare. This finding suggests that the theory of belief functions is a more general framework for classifier construction than is usually considered.
Fichier principal
Vignette du fichier
belief2018_logreg.pdf (740.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02553205 , version 1 (24-04-2020)

Identifiants

Citer

Thierry Denoeux. Logistic regression revisited: belief function analysis. 5th International Conference on Belief Functions (BELIEF 2018), Sep 2018, Compiègne, France. pp.57-64, ⟨10.1007/978-3-319-99383-6_8⟩. ⟨hal-02553205⟩
39 Consultations
79 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More