Naslov
Dynamic Neutral Network with Adaptive Neuron Activation Function

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

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

Izvornik
Annals od DAAAM for 2003 & Preceedings of 14th International DAAAM Symposium Intelligent Manufacturing & Automatation : Focus on Recostruction and Development (ISSN 1726-9679) / Katalinic, Branko - Beč : DAAAM International Vienna, 2003, 285-286

Skup
International DAAAM Symposium (14 ; 2003)

Mjesto i datum
Sarajevo, Bosna i Hercegovina, 22.10.2003. - 25.10.2003

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
dynamic neural network; adaptive neuron activation function; momentum; prediction; Glass-Mackey

Sažetak
An attempt has been made to establish a nonlinear dynamic discrete-time neuron model, the so called Dynamic Elementary Processor (DEP). This dynamic neuron disposes of local memory, in that it has dynamic states. To accelerate the convergence of proposed extended dynamic error back propagation learning algorithm, the adaptive neuron activation function and momentum method are applied. Instead of most popular bipolar and unipolar Sigmoid neuron activation functions, the Gauss activation function with adaptive parameters is proposed. Based on the DEP neuron with adaptive activation function in hidden layer, a Dynamic Multi Layer Neural Network is proposed and tested in prediction of a Glass-Mackey time series.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA