IMI-BAS BAS
 

BulDML at Institute of Mathematics and Informatics >
ITHEA >
International Book Series Information Science and Computing >
2009 >
Book 08 Classification Forecasting Data Mining >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10525/1184

Title: Classification of Data to Extract Knowledge from Neural Networks
Authors: Martinez, Ana
Castellanos, Angel
Gonzalo, Rafael
Keywords: Neural Network
Backpropagation
Control Feedback Methods
Models of Computation
Issue Date: 2009
Publisher: Institute of Information Theories and Applications FOI ITHEA
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.
URI: http://hdl.handle.net/10525/1184
ISSN: 1313-0455
Appears in Collections:Book 08 Classification Forecasting Data Mining

Files in This Item:

File Description SizeFormat
ibs-08-p03.pdf65.19 kBAdobe PDFView/Open

 



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

 

Valid XHTML 1.0!   Creative Commons License DSpace Software Copyright © 2002-2009  The DSpace Foundation - Feedback