Publications:Fuzzy combination schemes for modular neural networks

From ISLAB/CAISR
Jump to navigationJump to search

Do not edit this section

Property "Publisher" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user.

Keep all hand-made modifications below

Title Fuzzy combination schemes for modular neural networks
Author
Year 1997
PublicationType Conference Paper
Journal
HostPublication SCIA '97, the 10th Scandinavian conference on image analysis : proceedings
Conference the 10th Scandinavian Conference on Image Analysis, Lappeenranta, Finland, June 9-11, 1997
DOI
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:544722
Abstract

In this paper, we discuss some new methods for combining different outputs from several feed forward neural networks into a final output. We generalize the BADD defuzzification method (G-BADD) to obtain substantial improvement in system output. It is compared with the ordinary BADD-, Sugeno- and the MOM-methods. The use of the fuzzy integral, as a selection tool when deciding which networks are to be used in the combination, is introduced.