Title :
Optimal hyperplane classifier based on entropy number bound
Author_Institution :
Electrotech. Lab., Ibaraki, Japan
Abstract :
Entropy number bound is a capacity measure for learning machines, proposed by Williamson et. al. (1998). Based on this capacity measure and the structural risk minimization principle, we actually implement an optimal hyperplane classifier. In online character recognition experiment using the tangent distance, our method performed better than the conventional optimal hyperplane classifier based on VC dimension
Keywords :
pattern classification; capacity measure; entropy number bound; learning machines; online character recognition experiment; optimal hyperplane classifier; structural risk minimization principle; tangent distance;
Conference_Titel :
Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)
Conference_Location :
Edinburgh
Print_ISBN :
0-85296-721-7
DOI :
10.1049/cp:19991145
