Neural modelling of fuzzy set connectives

Kaoru Hirota; Witold Pedrycz

doi:10.1117/12.165044

Neural modelling of fuzzy set connectives

Research output: Contribution to journal › Conference article › peer-review

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-monotonic and compensative properties. Numerical studies including the Zimmermann-Zysno data set illustrate the performance of the network.

Original language	English
Pages (from-to)	414-425
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	2061
DOIs	https://doi.org/10.1117/12.165044
Publication status	Published - 22 Dec 1993
Externally published	Yes
Event	Applications of Fuzzy Logic Technology 1993 - Boston, United States Duration: 7 Sept 1993 → 10 Sept 1993

Access to Document

10.1117/12.165044

Cite this

Hirota, K., & Pedrycz, W. (1993). Neural modelling of fuzzy set connectives. Proceedings of SPIE - The International Society for Optical Engineering, 2061, 414-425. https://doi.org/10.1117/12.165044

@article{2043ea1fccf94b17964d3aca62d81fad,

title = "Neural modelling of fuzzy set connectives",

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-monotonic and compensative properties. Numerical studies including the Zimmermann-Zysno data set illustrate the performance of the network.",

author = "Kaoru Hirota and Witold Pedrycz",

year = "1993",

month = dec,

day = "22",

doi = "10.1117/12.165044",

language = "English",

volume = "2061",

pages = "414--425",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Neural modelling of fuzzy set connectives

AU - Hirota, Kaoru

AU - Pedrycz, Witold

PY - 1993/12/22

Y1 - 1993/12/22

N2 - 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-monotonic and compensative properties. Numerical studies including the Zimmermann-Zysno data set illustrate the performance of the network.

AB - 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-monotonic and compensative properties. Numerical studies including the Zimmermann-Zysno data set illustrate the performance of the network.

UR - http://www.scopus.com/inward/record.url?scp=85075946966&partnerID=8YFLogxK

U2 - 10.1117/12.165044

DO - 10.1117/12.165044

M3 - Conference article

AN - SCOPUS:85075946966

SN - 0277-786X

VL - 2061

SP - 414

EP - 425

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Applications of Fuzzy Logic Technology 1993

Y2 - 7 September 1993 through 10 September 1993

ER -

Neural modelling of fuzzy set connectives

Abstract

Access to Document

Other files and links

Fingerprint

Cite this