Max-min fuzzy neural networks for solving relational equations.

Título inglés	Max-min fuzzy neural networks for solving relational equations.
Título español	Redes neuronales difusas de max-min para la resolución de ecuaciones relacionales.
Autor/es	Blanco, Armando ; Delgado, Miguel ; Requena, Ignacio
Organización	Dep. Cienc. Comput. Intel. Artif. Esc. Téc. Super. Ing. Inform. Granada, Granada, España
Revista	1134-5632
Publicación	1994, 1 (3): 335-345, 5 Ref.
Tipo de documento	articulo
Idioma	Inglés
Resumen inglés	The Relational Equations approach is one of the most usual ones for describing (Fuzzy) Systems and in most cases, it is the final expression for other descriptions. This is why the identification of Relational Equations from a set of examples has received considerable atention in the specialized literature. This paper is devoted to this topic, more specifically to the topic of max-min neural networks for identification. Three methods of learning Fuzzy Systems are developed by combining the most desirable properties of two existing ones: Sayto-Mukaidono's technique and the so called smoothed derivative technique.
Clasificación UNESCO	120110
Palabras clave español	Redes neuronales ; Algebras difusas ; Algebra relacional ; Criterio minimax
Código Z-Math	Zbl 0833.68111
Acceso al artículo completo