Pré-Publication, Document De Travail Année : 2020

Matrix Formulas for Semilinear Backpropagation

Résumé

The present article is a direct continuation of, and should be read concurrently with, reference [1]. In that paper formulas were obtained for the gradient of the quadratic error of a general differentiable multilayer neural network defined over Hilbert spaces. The formulas belong to the class of backpropagation procedures that express the gradient in terms of the output errors and the transpose partial derivatives of the layers. Here we first develop a mathematical framework for semilinear perceptron neural networks using the natural correspondence between the transpose partial derivatives and the transpose partial Jacobians of the layers, such Jacobians being expressed in terms of the perceptron data as equations (11) and (14). The final gradient formulas for perceptron networks are presented as equations (16) and (17). Section §14 contains figures with captions to complement the discussion.

Fichier principal
Vignette du fichier
Crespin, D. - Matrix Formulas for Semilinear Backpropagation.pdf (380.6 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02949853 , version 1 (26-09-2020)

Licence

Identifiants

  • HAL Id : hal-02949853 , version 1

Citer

Daniel Crespin. Matrix Formulas for Semilinear Backpropagation. 2020. ⟨hal-02949853⟩
206 Consultations
312 Téléchargements

Partager

  • More