An approach to synthesis of adaptive recurrent neural networks for robot control (CROSBI ID 464556)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Novaković, Branko ; Majetić, Dubravko
engleski
An approach to synthesis of adaptive recurrent neural networks for robot control
Abstract - In this paper a new algorithm for synthesis of adaptive recurrent discrete-time neural networks (NN) is proposed. For this purpose the following concepts are employed: (i) time-varying NN weights distribution in interaction weight matrix, (ii) one-step learning iteration approach in off-line learning of recurrent NN (RNN), and (iii) adaptation of RNN during the NN working phase by employing a new structure of a dynamic back-propagation neural network in on-line learning. Following the proposed NN synthesis procedure the adaptive recurrent NN for an adaptive nonlinear robot control is designed.
Recurrent neural network; adaptation; robot control
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
125-128-x.
1996.
nije evidentirano
objavljeno
Podaci o matičnoj publikaciji
Proceedings-KoREMA"96-41st Annual Conference, Vol. 2
Vukic, Zoran
Zagreb: Hrvatsko društvo za komunikacije, računarstvo, elektroniku, mjerenja I automatiku (KoREMA)
Podaci o skupu
KoREMA '96 41st Annual Conference
predavanje
18.09.1996-20.09.1996
Opatija, Hrvatska