Korbicz, Józef - red. ; Uciński, Dariusz - red.
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. ; 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.
Zielona Góra: Uniwersytet Zielonogórski
AMCS, Volume 22, Number 2 (2012) ; kliknij tutaj, żeby przejść
Biblioteka Uniwersytetu Zielonogórskiego
2021-09-08
2018-09-04
160
https://zbc.uz.zgora.pl/repozytorium/publication/55099
Nazwa wydania | Data |
---|---|
Backpropagation generalized delta rule for the selective attention Sigma-if artificial neural network | 2021-09-08 |
Hofreiter, Milan Zítek, Pavel Korbicz, Józef - red. Uciński, Dariusz - red.
Szymczyk, Piotr Tomecka-Suchoń, Sylwia Szymczyk, Magdalena Iacono, Mauro - ed. Kołodziej, Joanna - ed.
Florkowski, Marcin Rongińska, Tatiana - red.
Khrouf, F. Tebassi, Hamid Yallese, M.A. Chaoui, Kamel Haddad, A. Jurczak, Paweł - red.
Zítek, Pavel Mánková, Renata Hlava, Jaroslav Korbicz, Józef - red. Patton, Ronald J. - red.
Płonka, Lesław Kuczyński, Tadeusz - red.
Rybka, Jan Janicki, Artur Korbicz, Józef - red. Uciński, Dariusz - red.
Kumar, D. Thresh Soleimani, Hamed Kannan, Govindan Abaev, Pavel - ed. Razumchik, Rostislav - ed. Kołodziej, Joanna - ed.