Title :
Generalizing Version Space Support Vector Machines for Non-Separable Data
Author :
Smirnov, E.N. ; Sprinkhuizen-Kuyper, I.G. ; Nikolaev, N.I.
Author_Institution :
MICC-IKAT, Maastricht Univ.
Abstract :
Although version space support vector machines (VSSVMs) are a successful approach to reliable classification, they are restricted to separable data. This paper proposes generalized VSSVMs (GVSSVMs) applicable for separable and non-separable data. We show that GVSSVMs can outperform existing reliable-classification approaches
Keywords :
pattern classification; support vector machines; nonseparable data; reliable classification; separable data; version space support vector machines; Bayesian methods; Conferences; Data mining; Educational institutions; Support vector machine classification; Support vector machines; Testing; Training data; Voting;
Conference_Titel :
Data Mining Workshops, 2006. ICDM Workshops 2006. Sixth IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2702-7
DOI :
10.1109/ICDMW.2006.86
