Are artificial neural networks black boxes?

Author

Benítez, J.M. ; Castro, J.L. ; Requena, I.

Author_Institution

Dept. de Ciencias de la Comput. e Inteligencia Artificial, Granada Univ., Spain

Volume

8

Issue

5

fYear

1997

fDate

9/1/1997 12:00:00 AM

Firstpage

1156

Lastpage

1164

Abstract

Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criticisms is their being black boxes, since no satisfactory explanation of their behavior has been offered. In this paper, we provide such an interpretation of neural networks so that they will no longer be seen as black boxes. This is stated after establishing the equality between a certain class of neural nets and fuzzy rule-based systems. This interpretation is built with fuzzy rules using a new fuzzy logic operator which is defined after introducing the concept of f-duality. In addition, this interpretation offers an automated knowledge acquisition procedure

Keywords

feedforward neural nets; fuzzy logic; fuzzy systems; knowledge acquisition; knowledge based systems; multilayer perceptrons; artificial intelligence; f-duality concept; feedforward neural networks; fuzzy additive systems; fuzzy logic; fuzzy rule-based systems; knowledge acquisition; multilayer perceptrons; Artificial intelligence; Artificial neural networks; Computer networks; Fuzzy logic; Fuzzy neural networks; Fuzzy systems; Knowledge based systems; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.623216

Filename

623216