Are artificial neural networks black boxes?
- 1 September 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 8 (5) , 1156-1164
- https://doi.org/10.1109/72.623216
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
This publication has 14 references indexed in Scilit:
- Fuzzy systems with defuzzification are universal approximatorsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1996
- Fuzzy logic controllers are universal approximatorsIEEE Transactions on Systems, Man, and Cybernetics, 1995
- Interpolation, completion, and learning fuzzy rulesIEEE Transactions on Systems, Man, and Cybernetics, 1994
- Fuzzy systems as universal approximatorsIEEE Transactions on Computers, 1994
- On the equivalence of neural nets and fuzzy expert systemsFuzzy Sets and Systems, 1993
- Functional equivalence between radial basis function networks and fuzzy inference systemsIEEE Transactions on Neural Networks, 1993
- NN-driven fuzzy reasoningInternational Journal of Approximate Reasoning, 1991
- Fuzzy Set Theory — and Its ApplicationsPublished by Springer Nature ,1991
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Fuzzy control of model carFuzzy Sets and Systems, 1985