PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A novel kernel method for clustering
Francesco Camastra and Alessandro Verri
IEEE Transaction on PAMI Volume 27, pp. 801-805, 2005.


Abstract—Kernel Methods are algorithms that, by replacing the inner product with an appropriate positive definite function, implicitly perform a nonlinear mapping of the input data into a high-dimensional feature space. In this paper, we present a kernel method for clustering inspired by the classical K-Means algorithm in which each cluster is iteratively refined using a one-class Support Vector Machine. Our method, which can be easily implemented, compares favorably with respect to popular clustering algorithms, like K-Means, Neural Gas, and Self-Organizing Maps, on a synthetic data set and three UCI real data benchmarks (IRIS data, Wisconsin breast cancer database, Spam database).

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:2911
Deposited By:Alessandro Verri
Deposited On:23 November 2006