TY - JOUR
TI - Data Selection for Neural Networks
AU - Kordos, Mirosław
TI - Data Selection for Neural Networks
AB - 
	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.
VL - 2016
IS - Volume 25
PY - 2017
SN - 1732-3916
C1 - 2083-8476
SP - 153
EP - 164
DO - 10.4467/20838476SI.16.012.6193
UR - https://ejournals.eu/en/journal/schedae-informaticae/article/data-selection-for-neural-networks
KW - Neural Networks
KW - Data Selection
KW - Feature Selection
KW - Instance Selection