]> 2026-04-04T20:34:26+02:00 Publications:Selecting variables for neural network committees 500 en <p>The aim of the variable selection is threefold: to reduce model complexity, to promote diversity of committee networks, and to find a trade-off between the accuracy and diversity of the networks. To achieve the goal, the steps of neural network training, aggregation, and elimination of irrelevant input variables are integrated based on the negative correlation learning (1) error function. Experimental tests performed on three real world problems have shown that statistically significant improvements in classification performance can be achieved from neural network committees trained according to the technique proposed.</p> third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006 http://dx.doi.org/10.1007/11759966_123 http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:239219 842 Advances in neural networks - ISNN 2006 : third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006 ; proceedings. I Conference Paper Lecture Notes in Computer Science ; 3971 837 Selecting variables for neural network committees 2006 2016-09-30T20:40:20Z 2457662.3613426 Selecting variables for neural network committees 500 0 plainlist list 1 [[:Publications:Selecting variables for neural network committees]] Selecting variables for neural network committees# QUERY02cbff110d1667678ad97c5f9414264b 500 [2,"smw-datavalue-property-restricted-annotation-use","Publisher"] Selecting variables for neural network committees# ERR6c155b5d70b69ddb590b4f2e73389c2a 500 [2,"smw-datavalue-property-restricted-annotation-use","Author"] Selecting variables for neural network committees# ERRe24f17e090c98448f3de99d03182b7b6