Abstract
|
<p>In this paper, we discuss some ne … <p>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.</p> the combination, is introduced.</p>
|
Author
|
Mikael Signahl +
, Antanas Verikas +
|
Conference
|
the 10th Scandinavian Conference on Image Analysis, Lappeenranta, Finland, June 9-11, 1997
|
Diva
|
http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:544722
|
EndPage
|
424 +
|
HostPublication
|
SCIA '97, the 10th Scandinavian conference on image analysis : proceedings +
|
PublicationType
|
Conference Paper +
|
Publisher
|
Pattern Recognition Society of Finland +
|
StartPage
|
419 +
|
Title
|
Fuzzy combination schemes for modular neural networks +
|
Year
|
1997 +
|
Has queryThis property is a special property in this wiki.
|
Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
, Publications:Fuzzy combination schemes for modular neural networks +
|
Categories |
Publication +
|
Modification dateThis property is a special property in this wiki.
|
30 September 2016 20:39:46 +
|