A. Atiya et Ag. Parlos, IDENTIFICATION OF NONLINEAR DYNAMICS USING A GENERAL SPATIOTEMPORAL NETWORK, Mathematical and computer modelling, 21(1-2), 1995, pp. 53-71
The so-called spatio-temporal neural network is considered. This is a
neural network where the conventional weight multiplication operation
is replaced by a linear filtering operation. General learning algorith
ms are derived for such a network, both in the discrete-time and in th
e continuous-time domains. The problem of deterministic nonlinear syst
em identification is considered as an application of spatio-temporal n
eural networks. Nonlinear system identification is one of the challeng
ing problems in the field of dynamic systems, with limited successful
results using conventional methods. Neural network approaches have so
far been encouraging, but further exploration is needed. The capabilit
ies of the derived algorithms and of the considered architectures to e
ffectively identify deterministic nonlinear systems is demonstrated th
rough examples.