Pregled bibliografske jedinice broj: 54169
A New Structure of Discrete Time Neural Networks
A New Structure of Discrete Time Neural Networks // Computational Methods for Smart Structures and Materials / Brebbia, C. A. ; Samartin, A. ; Galvez, S. V. (ur.).
Southampton: Wessex Institute of Technology Press, 2000. str. X35-X44 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 54169 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A New Structure of Discrete Time Neural Networks
Autori
Novaković, Branko ; Novaković, Dario
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Computational Methods for Smart Structures and Materials
/ Brebbia, C. A. ; Samartin, A. ; Galvez, S. V. - Southampton : Wessex Institute of Technology Press, 2000, X35-X44
Skup
Second International Conference on Computational Methods for Smart Structures and Materials
Mjesto i datum
Madrid, Španjolska, 19.06.2000. - 21.06.2000
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Discrete time neural networks; new structure; very fast learning
Sažetak
A new structure of discrete-time neural networks (NN) with a new very fast learning algorithm is proposed. For this purpose the following concepts are employed: (i) combination of input and output activation functions, (ii) input time-varying signal distribution, (iii) time-discrete domain synthesis and (iiii) one-step learning iteration approach. The problem of multiple input-output mappings of ( time-varying ) vectors is solved. A new algorithm for the direct inverse modelling of input/output nonquadratic systems is discussed. Simulation results based on the synthesis of a new structure of feedforward NN of an universal logical unit are presented. The proposed NN synthesis procedure is useful for applications to identification and control of nonlinear, very fast, dynamical systems.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
