Model selection in neural networks

被引：230

作者：

Anders, U ^{[1
]}

Korn, O ^{[1
]}

机构：

[1] ZEW, Ctr European Econ Res, D-68034 Mannheim, Germany

来源：

NEURAL NETWORKS | 1999年 / 12卷 / 02期

关键词：

neural networks; statistical inference; model selection; identification; information criteria; cross validation; pruning; Monte Carlo simulation;

D O I：

10.1016/S0893-6080(98)00117-8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this article, we examine how model selection in neural networks can be guided by statistical procedures such as hypothesis tests, information criteria and cross validation. The application of these methods in neural network models is discussed, paying attention especially to the identification problems encountered. We then propose five specification strategies based on different statistical procedures and compare them in a simulation study. As the results of the study are promising, it is suggested that a statistical analysis should become an integral part of neural network modeling. (C) 1999 Elsevier Science Ltd. All rights reserved.

引用

页码：309 / 323

页数：15

共 37 条

[11] HYPOTHESIS-TESTING WHEN A NUISANCE PARAMETER IS PRESENT ONLY UNDER THE ALTERNATIVE [J].