Yz. Tsypkin et al., Neural networks for identification of nonlinear systems under random piecewise polynomial disturbances, IEEE NEURAL, 10(2), 1999, pp. 303-312
The problem of identification of a nonlinear dynamic system is considered.
ii two-layer neural network is used for the solution of the problem. System
s disturbed with unmeasurable noise are considered, although it is known th
at the disturbance is a random piecewise polynomial process. Absorption pol
ynomials and nonquadratic loss functions are used to reduce the effect of t
his disturbance on the estimates of the optimal memory of the neural-networ
k model.