]> 2026-04-04T19:42:12+02:00 Publications:Selecting salient features for classification committees 500 en <p>We present a neural network based approach for identifying salient features for classification in neural network committees. 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 of the network when learning a classification task. Feature selection is based on two criteria, namely the reaction of the cross-validation data set classification error due to the removal of the individual features and the diversity of neural networks comprising the committee. The algorithm developed removed a large number of features from the original data sets without reducing the classification accuracy of the committees. By contrast, the accuracy of the committees utilizing the reduced feature sets was higher than those exploiting all the original features. © Springer-Verlag Berlin Heidelberg 2003.</p> Joint International Conference on Artificial Neural Networks (ICANN)/International on Neural Information Processing (ICONIP), JUN 26-29, 2002, ISTANBUL, TURKEY http://dx.doi.org/10.1007/3-540-44989-2_5 http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:1195746 42 Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003 Conference Paper Lecture Notes in Computer Science ; 2714 35 Selecting salient features for classification committees 2714 2003 2018-04-07T06:48:33Z 2458215.7837153 Selecting salient features for classification committees 500 0 plainlist list 1 [[:Publications:Selecting salient features for classification committees]] Selecting salient features for classification committees# QUERY1c5a27bab3ed8976ac2439fcbcb9ba72 500 [2,"smw-datavalue-property-restricted-annotation-use","Publisher"] Selecting salient features for classification committees# ERR6c155b5d70b69ddb590b4f2e73389c2a 500 [2,"smw-datavalue-property-restricted-annotation-use","Author"] Selecting salient features for classification committees# ERRe24f17e090c98448f3de99d03182b7b6