Determining the orders of feature and hidden unit prunings of artificial neural networks

Simple item page
dc.contributor.authorJearanaitanakij, Kietikul
dc.contributor.authorPinngern, Ouen
dc.date.accessioned2026-08-06T09:53:26Z
dc.date.available2026-08-06T09:53:26Z
dc.date.issued2005-12-01
dc.description.abstractThere is a great deal of research undertaken for pruning away features and hidden units in order to reduce the size of Artificial Neural Networks (ANNs). However, none of these methods mentions about the relationship between the pruned unit and the number of epochs needed for retraining when the unit is pruned away from the network. In this paper, we present two heuristics for determining the pruning orders, which lead to the near smallest number of retraining epochs. The heuristics are based on the employment of the modified information gain calculated from all features in training data. Then, we test our proposed heuristics on an exclusive-or data set. The experimental results show the success of using information gain as a criterion for determining the pruning orders. © 2005 IEEE.
dc.identifier.citation2005 Fifth International Conference on Information Communications and Signal Processing, 2005, 353-356, 2005
dc.identifier.other2-s2.0-34147145485
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/1101
dc.source2005 Fifth International Conference on Information Communications and Signal Processing
dc.subjectArtificial neural networks
dc.subjectFeature pruning
dc.subjectHidden unit pruning
dc.subjectInformation gain
dc.subjectPruning order
dc.titleDetermining the orders of feature and hidden unit prunings of artificial neural networks
dc.typeConference Paper

Files

Collections

Research