Naslov
Modified Dynamic Neuron Model

Autori
Majetić, Dubravko ; Brezak, Danko ; Kasać, Josip ; Novaković, Branko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
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), 2007, 203-208

ISBN
978-953-97171-9-8

Skup
11th International Scientific Conference on Production Engineering CIM'2007.

Mjesto i datum
Biograd na Moru, Hrvatska, 13.06.2007. - 17.06.2007

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
dynamic neural network; adaptive activation function; bias neuron; error back-propagation; RPROP

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA