∂ is for Dialectica - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

∂ is for Dialectica

Résumé

Automatic Differentiation is the study of the efficient computation of differentials. While the first automatic differentiation algorithms are concomitant with the birth of computer science, the specific backpropagation algorithm has been brought to a modern light by its application to neural networks. In this work, we unveil a surprising connection between backpropagation and Gödel's Dialectica interpretation, a logical translation that realizes semi-classical axioms. This unexpected correspondence is exploited through different logical settings. It opens the way for explorations on the logical power of automatic differentiation algorithms.
Fichier principal
Vignette du fichier
dialectica_hal.pdf (446.68 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03123968 , version 1 (28-01-2021)
hal-03123968 , version 2 (04-02-2021)
hal-03123968 , version 3 (24-01-2022)

Identifiants

  • HAL Id : hal-03123968 , version 3

Citer

Marie Kerjean, Pierre-Marie Pédrot. ∂ is for Dialectica. 2022. ⟨hal-03123968v3⟩
243 Consultations
796 Téléchargements

Partager

Gmail Facebook X LinkedIn More