Homogeneous Artificial Neural Network - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2023

Homogeneous Artificial Neural Network

Abstract

The paper proposes an artificial neural network (ANN) being a global approximator for a special class of functions, which are known as generalized homogeneous. The homogeneity means a symmetry of a function with respect to a group of transformations having topological characterization of a dilation. In this paper, a class of the so-called linear dilations is considered. A homogeneous universal approximation theorem is proven. Procedures for an upgrade of an existing ANN to a homogeneous one are developed. Theoretical results are supported by examples from the various domains (computer science, systems theory and automatic control).
Fichier principal
Vignette du fichier
HANN.pdf (17.17 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04313941 , version 1 (29-11-2023)

Licence

Identifiers

  • HAL Id : hal-04313941 , version 1

Cite

Andrey Polyakov. Homogeneous Artificial Neural Network. 2023. ⟨hal-04313941⟩
63 View
54 Download

Share

Gmail Mastodon Facebook X LinkedIn More