A FUNCTIONAL EQUATION WITH POLYNOMIAL SOLUTIONS AND APPLICATION TO NEURAL NETWORKS - Sorbonne Université
Journal Articles Comptes Rendus. Mathématique Year : 2020

A FUNCTIONAL EQUATION WITH POLYNOMIAL SOLUTIONS AND APPLICATION TO NEURAL NETWORKS

Abstract

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.
Fichier principal
Vignette du fichier
paper_hal.pdf (596.58 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

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

Identifiers

Cite

Bruno Després, Matthieu Ancellin. A FUNCTIONAL EQUATION WITH POLYNOMIAL SOLUTIONS AND APPLICATION TO NEURAL NETWORKS. Comptes Rendus. Mathématique, 2020, Tome 358 (2020) no. 9-10, pp. 1059-1072, ⟨10.5802/CRMATH.124⟩. ⟨hal-02959678v3⟩
532 View
354 Download

Altmetric

Share

More