]> 2026-04-04T16:38:28+02:00 Publications:Selecting neural networks for a committee decision 500 en <p>To improve recognition results, decisions of multiple neural networks can be aggregated into a committee decision. In contrast to the ordinary approach of utilizing all neural networks available to make a committee decision, we propose creating adaptive committees, which are specific for each input data point. A prediction network is used to identify classification neural networks to be fused for making a committee decision about a given input data point. The jth output value of the prediction network expresses the expectation level that the jth classification neural network will make a correct decision about the class label of a given input data point. The proposed technique is tested in three aggregation schemes, namely majority vote, averaging, and aggregation by the median rule and compared with the ordinary neural networks fusion approach. The effectiveness of the approach is demonstrated on two artificial and three real data sets.</p> http://dx.doi.org/10.1142/S0129065702001229 http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:285853 361 5 International Journal of Neural Systems Journal Paper 351 Selecting neural networks for a committee decision 12 2002 2016-09-30T20:41:40Z 2457662.3622685 Selecting neural networks for a committee decision 500 0 plainlist list 1 [[:Publications:Selecting neural networks for a committee decision]] Selecting neural networks for a committee decision# QUERYa897a2c50a892359851e01a1a1ec5ece 500 [2,"smw-datavalue-property-restricted-annotation-use","Publisher"] Selecting neural networks for a committee decision# ERR6c155b5d70b69ddb590b4f2e73389c2a 500 [2,"smw-datavalue-property-restricted-annotation-use","Author"] Selecting neural networks for a committee decision# ERRe24f17e090c98448f3de99d03182b7b6