Neural modelling of fuzzy set connectives

Kaoru Hirota; Witold Pedrycz

doi:10.1117/12.165044

Translator Disclaimer

22 December 1993 Neural modelling of fuzzy set connectives

Kaoru Hirota, Witold Pedrycz

Author Affiliations +

Proceedings Volume 2061, Applications of Fuzzy Logic Technology; (1993) https://doi.org/10.1117/12.165044
Event: Optical Tools for Manufacturing and Advanced Automation, 1993, Boston, MA, United States

Abstract

The paper introduces a neural network-based model of logical connectives. The network consists of two types of generic OR and AND neurons structured into a three layer topology. The specificity of the logical connectives is captured by the network within its supervised learning. Further analysis of the connections of the network obtained in this way provides a better insight into the nature of the connectives for fuzzy sets; in particular the analysis can look at their non-monotomic and compensative properties. Numerical studies including the Zimmermann-Zysno data set illustrate the performance of the network.

Citation Download Citation

Kaoru Hirota and Witold Pedrycz "Neural modelling of fuzzy set connectives", Proc. SPIE 2061, Applications of Fuzzy Logic Technology, (22 December 1993); https://doi.org/10.1117/12.165044

ACCESS THE FULL ARTICLE