Title :

Homogeneous Artificial Neural Network

Author(s) :

Polyakov, Andrey [Auteur]
Finite-time control and estimation for distributed systems [VALSE]

English keyword(s) :

homogeneous function
artificial neural network

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Systèmes et contrôle [cs.SY]
Mathématiques [math]/Systèmes dynamiques [math.DS]

English abstract : [en]

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 ...
Show more >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).Show less >

Language :

Anglais

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL