PARSIMONIOUS DYNAMICAL RECONSTRUCTION

被引：35

作者：

Mees, Alistair ^{[1
]}

机构：

[1] Univ Western Australia, Dept Math, Nedlands, WA 6009, Australia

来源：

INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS | 1993年 / 3卷 / 03期

基金：

澳大利亚研究理事会;

关键词：

D O I：

10.1142/S021812749300057X

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

Many nonlinear deterministic models of time series have large numbers of parameters and tend to overfit in the presence of noise. This paper shows how to generate radial basis function models with small numbers of parameters for a given quality of fit. It also addresses questions of how to select subsets from candidate sets of centers for radial basis function models, and what kinds of basis functions to use, as well as how large a model is appropriate.

引用

页码：669 / 675

页数：7

共 20 条

[1] Broomhead D. S., 1988, Complex Systems, V2, P321
[2] NONLINEAR PREDICTION OF CHAOTIC TIME-SERIES
CASDAGLI, M
[J]. PHYSICA D, 1989, 35 (03): : 335 - 356
[3] ORTHOGONAL LEAST-SQUARES LEARNING ALGORITHM FOR RADIAL BASIS FUNCTION NETWORKS
CHEN, S
COWAN, CFN
GRANT, PM
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (02): : 302 - 309
[4] PREDICTING CHAOTIC TIME-SERIES
FARMER, JD
SIDOROWICH, JJ
[J]. PHYSICAL REVIEW LETTERS, 1987, 59 (08) : 845 - 848
[5] MEASURING THE STRANGENESS OF STRANGE ATTRACTORS
GRASSBERGER, P
PROCACCIA, I
[J]. PHYSICA D, 1983, 9 (1-2): : 189 - 208
[6] Huberman B., 1990, BACK PROPAGATION WEI, V1990
[7] AN IMPROVED ESTIMATOR OF DIMENSION AND SOME COMMENTS ON PROVIDING CONFIDENCE-INTERVALS
JUDD, K
[J]. PHYSICA D, 1992, 56 (2-3): : 216 - 228
[8] ESTIMATING DIMENSIONS WITH CONFIDENCE
Judd, Kevin
Mees, Alistair I.
[J]. INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 1991, 1 (02): : 467 - 470
[9] LeBaron B., 1991, PERSISTENCE DOW JONE
[10] Mees A., 1990, DYNAMICS COMPLEX INT, P104

← 1 2 →