Title :
Error estimation of recurrent neural network models trained on a finite set of initial values
Author :
Liu, Binfan ; Si, Jennie
Author_Institution :
Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ, USA
Abstract :
Addresses the problem of estimating training error bounds of state and output trajectories for a class of recurrent neural networks as models of nonlinear dynamic systems. The bounds are obtained provided that the models have been trained on N trajectories with N independent random initial values which are uniformly distributed over [a, b]m εℛm
Keywords :
learning (artificial intelligence); multilayer perceptrons; nonlinear dynamical systems; recurrent neural nets; error estimation; nonlinear dynamic systems; output trajectories; random initial values; recurrent neural network models; state trajectories; training error bounds; Control systems; Error analysis; Multi-layer neural network; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Recurrent neural networks; State estimation; Time series analysis; Trajectory;
Conference_Titel :
Decision and Control, 1997., Proceedings of the 36th IEEE Conference on
Print_ISBN :
0-7803-4187-2
DOI :
10.1109/CDC.1997.657716
