%0 Journal Article
%T Data Selection for Neural Networks
%A Kordos, Mirosław
%J Schedae Informaticae
%V 2016
%R 10.4467/20838476SI.16.012.6193
%N Volume 25
%P 153-164
%K Neural Networks, Data Selection, Feature Selection, Instance Selection
%@ 1732-3916
%D 2017
%U https://ejournals.eu/en/journal/schedae-informaticae/article/data-selection-for-neural-networks
%X 
	Several approaches to joined feature and instance selection in neural network leaning are discussed and experimentally evaluated in respect to classification accuracy and dataset compression, considering also their computational complexity. These include various versions of feature and instance selection prior to the network learning, the selection embedded in the neural network and hybrid approaches, including solutions developed by us. The advantages and disadvantages of each approach are discussed and some possible improvements are proposed.