A FUNCTIONAL EQUATION WITH POLYNOMIAL SOLUTIONS AND APPLICATION TO NEURAL NETWORKS - Sorbonne Université
Pré-Publication, Document De Travail Année : 2020

A FUNCTIONAL EQUATION WITH POLYNOMIAL SOLUTIONS AND APPLICATION TO NEURAL NETWORKS

Résumé

We construct and discuss a functional equation with contraction property. The solutions are real univariate polynomials. The series solving the natural fixed point iterations have immediate interpretation in terms of Neural Networks with recursive properties and controlled accuracy.
We construct and discuss a functional equation with contraction property. The solutions are real univariate polynomials. The series solving the natural fixed point iterations have immediate interpretation in terms of Neural Networks with recursive properties and controlled accuracy.

Domaines

Analyse numérique [math.NA] Intelligence artificielle [cs.AI]
Fichier principal
Vignette du fichier
paper_hal.pdf (595.75 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Bruno Després  : Connectez-vous pour contacter le contributeur

https://hal.sorbonne-universite.fr/hal-02959678

Soumis le : vendredi 9 octobre 2020-08:12:00

Dernière modification le : lundi 15 avril 2024-11:25:23

Télécharger pour visualiser

Dates et versions

hal-02959678 , version 1 (07-10-2020)
hal-02959678 , version 2 (09-10-2020)
hal-02959678 , version 3 (24-11-2020)

Identifiants

  • HAL Id : hal-02959678 , version 2

Citer

Bruno Després, Matthieu Ancellin. A FUNCTIONAL EQUATION WITH POLYNOMIAL SOLUTIONS AND APPLICATION TO NEURAL NETWORKS. 2020. ⟨hal-02959678v2⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite
561 Consultations
371 Téléchargements

Partager

More