Description: er than mean squared error (MSE) function only. As an additional merit,
it is also revealed that rigorous Mercer kernel condition is not required in FKNN networks. When the
proposed
architecture of FKNN networks is constructed in a layer-by-layer way, i.e., the number of the
hidden
nodes of every hidden layer may be determined only in terms of the extracted principal com-
ponents
after the explicit execution of a KPCA, we can develop FKNN’s deep architecture such that its
deep
learning framework (DLF) has strong theoretical guarantee. Our experimental results about image
classification
manifest that the proposed FKNN’s deep architecture and its DLF based learning indeed
enhance
the classification performance
To Search:
File list (Check if you may need any files):
1-s2.0-S1568494615004809-main.pdf
Download