The evidence framework applied to support vector machines

被引：110

作者：

Kwok, JTY ^{[1
]}

机构：

[1] Hong Kong Baptist Univ, Dept Comp Sci, Hong Kong, Peoples R China

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2000年 / 11卷 / 05期

关键词：

Bayesian inference; evidence framework; support vector machine (SVM);

D O I：

10.1109/72.870047

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 paper, we show that training of the support vector machine (SVM) can be interpreted as performing the level 1 inference of MacKay's evidence framework. We further on show that levels 2 and 3 of the evidence framework can also be applied to SVMs. This integration allows automatic adjustment of the regularization parameter and the kernel parameter to their near-optimal values, Moreover, it opens up a wealth of Bayesian tools for use with SVMs. Performance of this method is evaluated on both synthetic and real-world data sets.

引用

页码：1162 / 1173

页数：12

共 21 条

[11] INFORMATION-BASED OBJECTIVE FUNCTIONS FOR ACTIVE DATA SELECTION [J].

MACKAY, DJC .

NEURAL COMPUTATION, 1992, 4 (04) :590-604

[12] A PRACTICAL BAYESIAN FRAMEWORK FOR BACKPROPAGATION NETWORKS [J].

MACKAY, DJC .

NEURAL COMPUTATION, 1992, 4 (03) :448-472

[13]

MULLER KR, 1997, P INT C ART NEUR NET, P999

[14]

NEAL RM, 1996, SER LECT NOTES STAT

[15]

SCHOLKOPF B, 1997, THESIS TU BERLIN BER

[16] The connection between regularization operators and support vector kernels [J].

Smola, AJ ;

Scholkopf, B ;

Muller, KR .

NEURAL NETWORKS, 1998, 11 (04) :637-649

[17]

SMOLA AJ, 1998, NC2TR1998030 NEUR RO

[18] Review of Bayesian neural networks with an application to near infrared spectroscopy [J].

Thodberg, HH .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (01) :56-72

[19]

Vapnik V, 1999, NATURE STAT LEARNING

[20]

Vapnik V., 1998, STAT LEARNING THEORY, V1, P2

← 1 2 3 →