Title :
A fast and robust recursive prediction error learning algorithm for feedforward neural networks
Author :
Zhang, Youmin ; Li, X. Rong
Author_Institution :
Dept. of Electr. Eng., New Orleans Univ., LA, USA
Abstract :
A fast and robust algorithm for training feedforward neural networks (FNNs) by using a variable forgetting factor and U-D factorization-based recursive prediction error (RPE) method is proposed. In comparison with the backpropagation (BP) and RPE based learning algorithms, the proposed algorithm, called UD-RPE, can provide much more accurate learning results in fewer iterations with fewer hidden nodes and improve convergence rate and numerical stability (robustness). In addition, it is less sensitive to start-up parameters, such as initial weights and initial covariance matrix, and the randomness in the observed data. It also has good generalization ability and needs less learning time. Simulation results of nonlinear dynamic system modeling and identification show that the algorithm proposed here is an effective and efficient learning algorithm for FNNs
Keywords :
feedforward neural nets; generalisation (artificial intelligence); learning (artificial intelligence); nonlinear dynamical systems; numerical stability; recursive estimation; U-D factorization-based recursive prediction error learning algorithm; backpropagation; convergence rate; feedforward neural networks; generalization ability; identification; nonlinear dynamic system modeling; numerical stability; variable forgetting factor; Backpropagation algorithms; Convergence of numerical methods; Covariance matrix; Feedforward neural networks; Neural networks; Nonlinear dynamical systems; Numerical stability; Prediction algorithms; Robust stability; Robustness;
Conference_Titel :
Decision and Control, 1996., Proceedings of the 35th IEEE Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-3590-2
DOI :
10.1109/CDC.1996.572884