Hierarchical learning in polynomial Support Vector Machines
Disordered Systems and Neural Networks
2009-09-25 v1
Abstract
We study the typical properties of polynomial Support Vector Machines within a Statistical Mechanics approach that allows us to analyze the effect of different normalizations of the features. If the normalization is adecuately chosen, there is a hierarchical learning of features of increasing order as a function of the training set size.
Keywords
Cite
@article{arxiv.cond-mat/0010423,
title = {Hierarchical learning in polynomial Support Vector Machines},
author = {Sebastian Risau-Gusman and Mirta B. Gordon},
journal= {arXiv preprint arXiv:cond-mat/0010423},
year = {2009}
}
Comments
22 pages, 7 figures, submitted to Machine Learning