Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach

It is well known that Artificial Neural Networks are universal approximators. The classical result proves that, given a continuous function on a compact set on an n-dimensional space, then there exists a one-hidden-layer feedforward network which approximates the function. Such result proves the exi...

Descripción completa

Detalles Bibliográficos
Autores: González Díaz, Rocío, Gutiérrez Naranjo, Miguel Ángel, Paluzo Hidalgo, Eduardo
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2019
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/97963
Acceso en línea:https://hdl.handle.net/11441/97963
Access Level:acceso abierto
Palabra clave:Universal approximation theorem
Simplicial approximation theorem
Multilayer feedforward network
Simplicial Complexes
Descripción
Sumario:It is well known that Artificial Neural Networks are universal approximators. The classical result proves that, given a continuous function on a compact set on an n-dimensional space, then there exists a one-hidden-layer feedforward network which approximates the function. Such result proves the existence, but it does not provide a method for finding it. In this paper, a constructive approach to the proof of this property is given for the case of two-hidden-layer feedforward networks. This approach is based on an approximation of continuous functions by simplicial maps. Once a triangulation of the space is given, a concrete architecture and set of weights can be obtained. The quality of the approximation depends on the refinement of the covering of the space by simplicial complexes.