Title :
The evidence framework applied to support vector machines
Author :
Kwok, James Tin-Yau
Author_Institution :
Dept. of Comput. Sci., Hong Kong Baptist Univ., China
fDate :
9/1/2000 12:00:00 AM
Abstract :
We show that training of the support vector machine (SVM) can be interpreted as performing the level 1 inference of MacKay´s evidence framework (1992). 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
Keywords :
Bayes methods; feedforward neural nets; inference mechanisms; learning (artificial intelligence); pattern classification; Bayesian inference; MacKay evidence framework; feedforward neural networks; learning; pattern classification; support vector machine; Bayesian methods; Councils; Kernel; Learning systems; Machine learning; Pattern recognition; Risk management; Support vector machines; Training data; Upper bound;
Journal_Title :
Neural Networks, IEEE Transactions on
