Bf. Liu et J. Si, ERROR ESTIMATION OF RECURRENT NEURAL-NETWORK MODELS TRAINED ON A FINITE-SET OF INITIAL VALUES, IEEE transactions on circuits and systems. 1, Fundamental theory andapplications, 44(11), 1997, pp. 1086-1089
This letter addresses the problem of estimating training error bounds
of state and output trajectories for a class of recurrent neural netwo
rks as models of nonlinear dynamic systems, The bounds are obtained pr
ovided that the models have been trained on N trajectories with N inde
pendent random initial values which are uniformly distributed over [a,
b](m) is an element of R-m.