Observatorio de I+D+i UPM

Descripción
A major drawback of artificial neural networks is their black-box character. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, we use a method that can be used for symbolic knowledge extraction from neural networks, once they have been trained with desired function. The basis of this method is the weights of the neural network trained. This method allows knowledge extraction from neural networks with continuous inputs and output as well as rule extraction. An example of the application is showed. This example is based on the extraction of average load demand of a power plant.
Internacional	Si
JCR del ISI	No
Título de la revista	INFORMATION SCIENCE & COMPUTING
ISSN	1313-0455
Factor de impacto JCR	0
Información de impacto
Volumen
DOI
Número de revista	8
Desde la página	20
Hasta la página	25
Mes	ENERO
Ranking

Esta actividad pertenece a memorias de investigación

• Autor: Ana Martinez Blanco (UPM)
• Autor: Angel Luis Castellanos Peñuela (UPM)
• Autor: Rafael Gonzalo Molina (UPM)

• Creador: Grupo de Investigación: Grupo de Computación Natural
• Departamento: Ciencias Básicas Aplicadas a la Ingeniería Forestal
• Departamento: Inteligencia Artificial