Abstract
|
<p>We present a neural network based … <p>We present a neural network based approach for identifying salient features for classification in feed-forward neural networks. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the cross-validation data set classification error due to the removal of the individual features. We compared the approach with five other feature selection methods, each of which banks on different concept. The algorithm developed outperformed the other methods by achieving a higher classification accuracy on all the problems tested.</p>racy on all the problems tested.</p>
|
Author
|
Antanas Verikas +
, Marija Bacauskiene +
, Kerstin Malmqvist +
|
Conference
|
8th International Conference on Neural Information Processing (ICONIP 2001), SHANGHAI, PEOPLES R CHINA, NOV 14-18, 2001
|
Diva
|
http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:545121
|
EndPage
|
68 +
|
HostPublication
|
Neural Information Precessing : ICONIP-2001 proceedings +
|
PublicationType
|
Conference Paper +
|
Publisher
|
Fudan University Press +
|
StartPage
|
63 +
|
Title
|
Selecting features with neural networks +
|
Year
|
2001 +
|
Has queryThis property is a special property in this wiki.
|
Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
, Publications:Selecting features with neural networks +
|
Categories |
Publication +
|
Modification dateThis property is a special property in this wiki.
|
30 September 2016 20:41:28 +
|