Discrete Time Neural Networks Synthesis Using Interaction Activation Functions (CROSBI ID 491052)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Novaković, Branko ; Pavić, Ante ; Novaković, Alen
engleski
Discrete Time Neural Networks Synthesis Using Interaction Activation Functions
A new structure of discrete time neural networks is proposed. For this purpose the following concepts are used: (i) an introduction of an interaction activation functions, (ii) input time-varying signal distribution, (iii) time discrete domain synthesis, and (iv) one step learning iteration procedure. Simulation results, based on the synthesis of a new structure of recurrent neural network of an universal logical unit are presented. The proposed neural network synthesis procedure is useful for applications to identification and control of nonlinear dynamics systems, like industrial robots.
Neural Networks; Discrete Time Synthesis; Interaction Activation Functions
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1097-1100-x.
2003.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of 7th International Research/Expert Conference "Trends in the Development of Machinery and Associated Technology - TMT 2003"
Vivancos, J. ; Pureta, F. ; Ekinović, S. ; Brdarević, S.
Barcelona: Universitat Politecnica de Catalunya ; University of Sarajevo
Podaci o skupu
Trends in the Development of Machinery and Associated Technology - TMT 2003
predavanje
15.09.2003-17.09.2003
Barcelona, Španjolska; Lloret de Mar, Španjolska