Fuzzy Connectives as a Combination Tool in a Hybrid Multi-Neural System

Canuto, Anne, Fairhurst, Michael, Howells, Gareth (2003) Fuzzy Connectives as a Combination Tool in a Hybrid Multi-Neural System. International Journal of Neural Systems, 13 (2). pp. 67-76. ISSN 0129-0657. (doi:10.1142/s0129065703001455) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:7592)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided.
Official URL: https://doi.org/10.1142/s0129065703001455

Abstract

The set of fuzzy connectives can be seen as an important combination tool, such as in combining the antecedent sets of the rules, in multi-criteria decision making and in combining the outputs of neural classifiers in a multi-neural system. This papers investigates the performance of some fuzzy combination schemes applied to a multi hybrid neural system which is composed of neural and fuzzy neural networks. An empirical evaluation in a handwritten numeral recognition task is used to investigate the performance of the presented fuzzy methods with some existing combination methods. [ABSTRACT FROM AUTHOR]

Item Type:	Article
DOI/Identification number:	10.1142/s0129065703001455
Subjects:	T Technology > TK Electrical engineering. Electronics. Nuclear engineering > TK7800 Electronics > TK7880 Applications of electronics > TK7885 Computer engineering. Computer hardware
Divisions:	Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
Depositing User:	Yiqing Liang
Date Deposited:	15 Sep 2008 10:45 UTC
Last Modified:	05 Nov 2024 09:39 UTC
Resource URI:	https://kar.kent.ac.uk/id/eprint/7592 (The current URI for this page, for reference purposes)

University of Kent Author Information

Fairhurst, Michael.

Creator's ORCID:
CReDIT Contributor Roles:

Howells, Gareth.

Creator's ORCID:	https://orcid.org/0000-0001-5590-0880
CReDIT Contributor Roles:

Depositors only (login required):

Altmetric

Download Statistics

Total unique views for this document in KAR since July 2020. For more details click on the image.