Optimisation of radial basis function neural networks using biharmonic spline interpolation

被引：40

作者：

Tetteh, J

Howells, S

Metcalfe, E ^{[1
]}

Suzuki, T

机构：

[1] Univ Greenwich, Sch Chem & Life Sci, London SE18 6PF, England

[2] Tokyo Inst Technol, Resources Utilizat Res Lab, Midori Ku, Yokohama, Kanagawa 226, Japan

来源：

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS | 1998年 / 41卷 / 01期

关键词：

splines; Green's function; response surface; optimisation; neural networks; radial basis functions;

D O I：

10.1016/S0169-7439(98)00035-5

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Biharmonic spline interpolation has been applied as an optimisation tool to study response surfaces of bi-directional data. Both regularly and randomly spaced training data yielded results with prediction errors in the range 0.1 to 10%. Practical application of the technique has been demonstrated by optimising both the spread parameter and the number of neurons in the hidden layer of radial basis function (RBF) neural networks. The efficiency and practical application of this optimisation approach is demonstrated by the prediction of the auto-ignition temperature (AIT) values of 232 organic compounds using quantitative structure-property relationships (QSPR) with six descriptors. It is concluded that this optimisation strategy is fast and provides a very flexible way of modelling non-linear systems in general. (C) 1998 Elsevier Science B.V. All rights reserved.

引用

页码：17 / 29

页数：13

共 16 条

[1]

Ahlberg JH., 1967, The Theory of Splines and Their Applications

[2]

*ASTM, 1994, E65978 ANSI ASTM

[3] BEYOND RESPONSE SURFACES - RECENT DEVELOPMENTS IN OPTIMUM EXPERIMENTAL-DESIGN [J].

ATKINSON, AC .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1995, 28 (01) :35-47

[4]

BERTHOLD MR, 1995, ADV NEURAL INFORMATI, V7, P521

[5]

Box GEP, 1987, Empirical model-building and response surfaces

[6]

Carlson R., 1992, DESIGN OPTIMIZATION

[7] ORTHOGONAL LEAST-SQUARES LEARNING ALGORITHM FOR RADIAL BASIS FUNCTION NETWORKS [J].

CHEN, S ;

COWAN, CFN ;

GRANT, PM .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (02) :302-309

[8]

COHN DA, 1994, 1491 MIT AI

[9]

*MATL MATHW, 1992, REF GUID

[10]

MESIAS JM, 1995, J ATMOS OCEAN TECH, V12, P830, DOI 10.1175/1520-0426(1995)012<0830:AIMTDO>2.0.CO

← 1 2 →