TY - GEN
A1 - Huk, Maciej
A2 - Korbicz, Józef - red.
A2 - Uciński, Dariusz - red.
PB - Zielona Góra: Uniwersytet Zielonogórski
N2 - In this paper the Sigma-if artificial neural network model is considered, which is a generalization of an MLP network with sigmoidal neurons. It was found to be a potentially universal tool for automatic creation of distributed classification and selective attention systems. To overcome the high nonlinearity of the aggregation function of Sigma-if neurons, the training process of the Sigma-if network combines an error backpropagation algorithm with the self-consistency paradigm widely used in physics.
N2 - But for the same reason, the classical backpropagation delta rule for the MLP network cannot be used. The general equation for the backpropagation generalized delta rule for the Sigma-if neural network is derived and a selection of experimental results that confirm its usefulness are presented.
L1 - http://zbc.uz.zgora.pl/Content/46994/AMCS_2012_22_2_17.pdf
L2 - http://zbc.uz.zgora.pl/Content/46994
KW - artificial neural networks
KW - selective attention
KW - self consistency
KW - error backpropagation
KW - delta rule
T1 - Backpropagation generalized delta rule for the selective attention Sigma-if artificial neural network
UR - http://zbc.uz.zgora.pl/dlibra/docmetadata?id=46994
ER -