A COMPARISON OF THE BACKPROPAGATION AND RECURSIVE PREDICTION ERROR ALGORITHMS FOR TRAINING NEURAL NETWORKS

被引：35
作者：
BILLINGS, SA
JAMALUDDIN, HB
CHEN, S
机构：
[1] Department of Control Engineering, University of Sheffield, Sheffield, S1 3JD, Mappin Street
[2] Department of Electrical Engineering, University of Edinburgh, Edinburgh, EH9 3JL, Mayfield Road
来源：
MECHANICAL SYSTEMS AND SIGNAL PROCESSING | 1991年 / 5卷 / 03期
关键词：
D O I：
10.1016/0888-3270(91)90045-7
中图分类号：
TH [机械、仪表工业];
学科分类号：
0802 ;
摘要：
A new recursive prediction error routine is compared with the backpropagation method of training neural networks. Results based on simulated systems, the prediction of Canadian lynx data, and the modelling of an automotive diesel engine indicate that the recursive prediction error algorithm is far superior to backpropagation. © 1991.
引用
收藏
页码：233 / 255
页数：23
相关论文
共 24 条
[1]  
Lippman, An Introduction to computing with neural nets, IEEE ASSP Magazine, (1987)
[2]  
Marmarelis, Marmarelis, White Noise Analysis of Physiological Systems, (1978)
[3]  
Leontaritis, Billings, Input-output parametric models for non-linear systems, Part I: Deterministic non-linear systems, International Journal of Control, 41, pp. 303-344, (1985)
[4]  
Leontaritis, Billings, Input-output parametric models for non-linear systems, Part II: Stochastic non-linear systems, International Journal of Control, 41, pp. 303-344, (1985)
[5]  
Lapedes, Farber, Nonlinear signal processing using neural networks: prediction and system modelling, Preprint LA-UR-87-2662, (1987)
[6]  
Chen, Billings, Grant, Non-linear systems identification using neural networks, International Journal of Control, 51, pp. 1191-1214, (1990)
[7]  
Cybenko, Approximations by superpositions of a sigmoidal function, Mathematics of Control, Signals and Systems, 2, pp. 303-314, (1989)
[8]  
Funahashi, On the approximate realization of continuous mappings by neural networks, Neural Networks, 2, pp. 183-192, (1989)
[9]  
Sejnowski, Rosenberg, NETtalk: a parallel network that learns to read aloud, Johns Hopkins University Technical Report JHU/EECS-86/01, (1986)
[10]  
Allen, Several studies on natural language and backpropagation, IEEE First International Conference on Neural Networks, 2, pp. 335-341, (1987)
123