DocumentCode :
1441972
Title :
The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks
Author :
Tickle, Alan B. ; Andrews, Robert ; Golea, Mostefa ; Diederich, Joachim
Author_Institution :
Neurocomput. Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
Volume :
9
Issue :
6
fYear :
1998
fDate :
11/1/1998 12:00:00 AM
Firstpage :
1057
Lastpage :
1068
Abstract :
To date, the preponderance of techniques for eliciting the knowledge embedded in trained artificial neural networks (ANN´s) has focused primarily on extracting rule-based explanations from feedforward ANN´s. The ADT taxonomy for categorizing such techniques was proposed in 1995 to provide a basis for the systematic comparison of the different approaches. This paper shows that not only is this taxonomy applicable to a cross section of current techniques for extracting rules from trained feedforward ANN´s but also how the taxonomy can be adapted and extended to embrace a broader range of ANN types (e,g., recurrent neural networks) and explanation structures. In addition we identify some of the key research questions in extracting the knowledge embedded within ANN´s including the need for the formulation of a consistent theoretical basis for what has been, until recently, a disparate collection of empirical results
Keywords :
explanation; feedforward neural nets; finite automata; knowledge acquisition; recurrent neural nets; ADT taxonomy; explanation structures; feedforward neural networks; finite state automata; fuzzy neural networks; knowledge acquisition; knowledge insertion; recurrent neural networks; rule extraction; rule refinement; Artificial neural networks; Automata; Feedforward neural networks; Function approximation; Fuzzy neural networks; Intelligent networks; Neural networks; Pattern recognition; Recurrent neural networks; Taxonomy;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/72.728352
Filename :
728352
Link To Document :
بازگشت