Determining the structures and parameters of radial basis function neural networks using improved genetic algorithms

被引：2

作者：

Meiqin Liu

Jida Chen

机构：

[1] Central South University of Technology,College of Information Engineering

来源：

Journal of Central South University of Technology | 1998年 / 5卷 / 2期

关键词：

radial basis function neural network; genetic algorithms; Akaike’s information criterion; overfitting;

D O I：

10.1007/s11771-998-0057-0

中图分类号：

学科分类号：

摘要：

The method of determining the structures and parameters of radial basis function neural networks (RBFNNs) using improved genetic algorithms is proposed. Akaike’s information criterion (AIC) with generalization error term is used as the best criterion of optimizing the structures and parameters of networks. It is shown from the simulation results that the method not only improves the approximation and generalization capability of RBFNNs, but also obtain the optimal or suboptimal structures of networks.

引用

页码：141 / 146

页数：5

共 8 条

[1]

Light W A(1992)Some aspects of radial basis function approximation Approximation Theory, Spline Functions and Applications 356 163-190

[2]

Bishop C M(1991)Improving the generalization properties of radial basis function neural network Neural Computation 3 579-588

[3]

Chen S(1990)Practical identification of NARMAX models using radial basis functions Int J Control 52 1327-1350

[4]

Billings S A(1993)Non-linear model term selection with genetic algorithms Proceedings of IEE/IEEE Workshop on Natural Algorithms in Signal Processing 2 271-278

[5]

Cowan C F N(undefined)undefined undefined undefined undefined-undefined

[6]

Fonseca C M(undefined)undefined undefined undefined undefined-undefined

[7]

Mendes E M(undefined)undefined undefined undefined undefined-undefined

[8]

Fleming P J(undefined)undefined undefined undefined undefined-undefined

← 1 →