Observatorio de I+D+i UPM

Memorias de investigación
Communications at congresses:
CLASSIFICATION OF DATA TO EXTRACT KNOWLEDGE FROM NEURAL NETWORKS
Year:2009
Research Areas
  • Artificial intelligence
Information
Abstract
Abstract: 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.
International
Si
Congress
"Information Research and Applications" (i.TECH 2009)
960
Place
Varna Bulgaria
Reviewers
Si
ISBN/ISSN
1313-0455
Start Date
24/06/2009
End Date
02/07/2009
From page
20
To page
27
International Book Series "INFORMATION SCIENCE & COMPUTING", Number 8 Supplement to the International Journal "INFORMATION TECHNOLOGIES & KNOWLEDGE" Volume 3, 2009
Participants
  • Autor: Angel Luis Castellanos Peñuela (UPM)
  • Autor: Ana Martinez Blanco (UPM)
Research Group, Departaments and Institutes related
  • Creador: Departamento: Ciencias Básicas Aplicadas a la Ingeniería Forestal
S2i 2019 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)