DocumentCode :
2616379
Title :
Reasoning Based on Rules Extracted from Trained Neural Networks via Formal Concept Analysis
Author :
Zarate, Luis ; Vimieiro, R. ; Vieira, N.
Author_Institution :
UNA Univ.
fYear :
0
fDate :
0-0 0
Firstpage :
1
Lastpage :
6
Abstract :
Due to their capability of dealing with nonlinear problems, artificial neural networks (ANN) are widely used with several purposes. Once trained, they are also capable of solving unprecedented situations, keeping tolerable errors in their outputs. However, ANN are considered essentially "black boxes". Therefore, humans can not assimilate the knowledge kept by those nets, since such knowledge is implicitly represented by their connection weights. In this paper, a new approach to extract knowledge rules from ANN previously trained through formal concept analysis is presented. The method allows to the knowledge engineer understand the industrial process that is being analyzed, through implications rules of the type if... then. As an example of application a solar energy system is considered. The rules obtained are validated through an expert domain
Keywords :
data analysis; inference mechanisms; knowledge acquisition; knowledge representation; learning (artificial intelligence); neural nets; artificial neural networks; formal concept analysis; knowledge engineering; knowledge representation; knowledge rule extraction; neural network training; nonlinear problem; reasoning; solar energy system; Application software; Artificial intelligence; Artificial neural networks; Data mining; Databases; Diseases; Humans; Knowledge representation; Neural networks; Solar energy;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering of Intelligent Systems, 2006 IEEE International Conference on
Conference_Location :
Islamabad
Print_ISBN :
1-4244-0456-8
Type :
conf
DOI :
10.1109/ICEIS.2006.1703141
Filename :
1703141
Link To Document :
بازگشت