]> 2026-04-04T20:34:29+02:00 Publications:Selecting features for neural network 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. 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 two other neural network based feature selection methods. The algorithm developed outperformed the methods by achieving a higher classification accuracy on three real world problems tested. ©2002 IEEE</p> International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 12-17 May, 2002 http://dx.doi.org/10.1109/IJCNN.2002.1005472 http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:1254348 220 Proceedings of the International Joint Conference on Neural Networks Conference Paper 215 Selecting features for neural network committees 2002 2018-10-09T20:22:28Z 2458401.3489352 Selecting features for neural network committees 500 0 plainlist list 1 [[:Publications:Selecting features for neural network committees]] Selecting features for neural network committees# QUERYbd275d0806687b96bc79d449341ef5ab 500 [2,"smw-datavalue-property-restricted-annotation-use","Publisher"] Selecting features for neural network committees# ERR6c155b5d70b69ddb590b4f2e73389c2a 500 [2,"smw-datavalue-property-restricted-annotation-use","Author"] Selecting features for neural network committees# ERRe24f17e090c98448f3de99d03182b7b6