Rapid design of neural networks for time series prediction

被引：23

作者：

Drossu, R ^{[1
]}

Obradovic, Z ^{[1
]}

机构：

[1] WASHINGTON STATE UNIV,SCH ELECT ENGN & COMP SCI,PULLMAN,WA 99164

来源：

IEEE COMPUTATIONAL SCIENCE & ENGINEERING | 1996年 / 3卷 / 02期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/99.503317

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Can a neural network be rapidly designed to predict a time series? Stochastic analysis can provide some initial knowledge about an appropriate NN architecture, parameter values, and data sampling rate. Such rapidly devised neural networks ar not optimal, but still perform similarly to NNs designed more elaborately through expensive trial-and-error procedures.

引用

页码：78 / 89

页数：12

共 14 条

[1]

[Anonymous], 1992, Handbook of Intelligent Control

[2]

BOX GEP, 1994, TIME SERIES ANAL

[3] RECURRENT NEURAL NETWORKS AND ROBUST TIME-SERIES PREDICTION [J].

CONNOR, JT ;

MARTIN, RD ;

ATLAS, LE .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :240-254

[4]

Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274

[5]

Drossu R., 1995, Computer Networks, Architecture and Applications. Proceedings of the IFIP TC6 Conference 1994, P146

[6]

Fletcher J., 1993, Connection Science, V5, P365, DOI 10.1080/09540099308915705

[7] Nonlinear black-box models in system identification: Mathematical foundations [J].

Juditsky, A ;

Hjalmarsson, H ;

Benveniste, A ;

Delyon, B ;

Ljung, L ;

Sjoberg, J ;

Zhang, QH .

AUTOMATICA, 1995, 31 (12) :1725-1750

[8]

Kay SM., 1988, Modern spectral estimation: theory and application

[9]

LAPEDES A, 1987, LAUR872662

[10]

POTTS MAS, 1991, SPIE ADAPTIVE SIGNAL, V1565, P255

← 1 2 →