Modified Dynamic Neuron Model (CROSBI ID 529650)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Majetić, Dubravko ; Brezak, Danko ; Kasać, Josip ; Novaković, Branko
engleski
Modified Dynamic Neuron Model
In this paper a modification of the nonlinear dynamic discrete-time neuron model, the so-called Dynamic Elementary Processor (DEP), is proposed. DEP disposes of local memory, in that it has dynamic states. Instead of the most popular unipolar and bipolar Sigmoidal neuron activation functions, the Gauss activation function with adaptive parameters is applied. Based on the DEP neurons in hidden layer a modified dynamic neural network (MDNN) without any Bias neurons is proposed. For such neural network, the Error Back- Propagation and RPROP learning strategies are compared in solving of two benchmarks, the Glass-Mackey time series prediction and XOR classification problem.
dynamic neural network; adaptive activation function; bias neuron; error back-propagation; RPROP
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
203-208-x.
2007.
objavljeno
Podaci o matičnoj publikaciji
Proceeding of 11th International Scientific Conference on Production Engineering CIM'2007., Computer Integrated Manufacturing and High Speed Machininig
Abele, Eberhard ; Udiljak, Toma ; Ciglar, Damir
Zagreb: Hrvatska udruga proizvodnog strojarstva (HUPS)
978-953-97171-9-8
Podaci o skupu
11th International Scientific Conference on Production Engineering CIM2007
predavanje
13.06.2007-17.06.2007
Biograd na Moru, Hrvatska