Recurrent neural network synthesis using interaction activation functions (CROSBI ID 464553)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Novaković, Branko
engleski
Recurrent neural network synthesis using interaction activation functions
Abstract - A new very fast algorithm for synthesis of recurrent discrete-time neural networks (NN) is proposed. For this purpose the following concepts are employed: (i) introduction of interaction activation functions, (ii) time-varying NN weights distribution, (iii) time-discrete domain synthesis and (iiii) one-step learning iteration approach.. The proposed NN synthesis procedure is useful for applications to identification and control of nonlinear, very fast, dynamical systems. In this sense a recurrent NN for a nonlinear robot control is designed.
Recurrent neural networks; interaction activation functions; one-step learning
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1608-1613-x.
1996.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of the 1996 IEEE International Conference on Robotics and Automation, Vol. 2
Norman Caplan
Minneapolis (MN): IEEE, The Institute of Electrical and Electronics Engineers, USA
Podaci o skupu
The 1996 IEEE International Conference on Robotics and Automation
predavanje
22.04.1996-28.04.1996
Minneapolis (MN), Sjedinjene Američke Države