Please use this identifier to cite or link to this item:
Title: Sobre las redes neuronales y la computación paralela
Authors: Bolívar Toledo, Olga
Muñoz Blanco, José Antonio 
Candela Solá, Santiago
Moreno Díaz, Roberto 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Visión artificial
Artificial vision
Issue Date: 1991
Journal: Revista de la Academia Canaria de Ciencias 
Abstract: Neurocybernetic, Systems Theory and Perception, and Artificial lntelligence Systems, interact in such a way that the methods and procedures of one of them provide clues in order to face and resolve problems in the others. This paper shows the interaction among the algebraic-analytical data fields theory, the complete descriptions that may be truncated for practical visual tasks and the structural-functional characteristics of neural nets. In this way, on researching the properties and requirements that complete descriptions had to verify, we may conclude that a general characteristic of transformations combining partitions and functionals, is the esentially parallel character of the computational structure that performs it. Then, the temporal factor, which had been forgotten in the former algebraic-analytical formulation has been introduced here, by considering layered and neural nets. This consideration allows's to clarify the reach and limitations of fast computational algorithms.
ISSN: 1130-4723
Source: Revista de la Academia Canaria de Ciencias = Folia Canariensis Academiae Scientiarum [ISSN 1130-4723], v. 3 (2), p. 95-103
Appears in Collections:Artículos
Adobe PDF (3,99 MB)
Show full item record

Page view(s)

checked on Jun 12, 2021


checked on Jun 12, 2021

Google ScholarTM



Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.