A PRACTICAL METHOD FOR SELF-ADAPTING GAUSSIAN EXPECTATION MAXIMIZATION
Nicola Greggio, Alexandre Bernardino, José Santos-Victor
2010
Abstract
Split-and-merge techniques have been demonstrated to be effective in overtaking the convergence problems in classical EM. In this paper we follow a split-and-merge approach and we propose a new EM algorithm that makes use of a on-line variable number of mixture Gaussians components. We introduce a measure of the similarities to decide when to merge components. A set of adaptive thresholds keeps the number of mixture components close to optimal values. For sake of computational burden, our algorithm starts with a low initial number of Gaussians, adjusting it in runtime, if necessary. We show the effectivity of the method in a series of simulated experiments. Additionally, we illustrate the convergence rates of of the proposed algorithms with respect to the classical EM.
DownloadPaper Citation
in Harvard Style
Greggio N., Bernardino A. and Santos-Victor J. (2010). A PRACTICAL METHOD FOR SELF-ADAPTING GAUSSIAN EXPECTATION MAXIMIZATION . In Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8425-00-3, pages 36-44. DOI: 10.5220/0002894600360044
in Bibtex Style
@conference{icinco10,
author={Nicola Greggio and Alexandre Bernardino and José Santos-Victor},
title={A PRACTICAL METHOD FOR SELF-ADAPTING GAUSSIAN EXPECTATION MAXIMIZATION},
booktitle={Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2010},
pages={36-44},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002894600360044},
isbn={978-989-8425-00-3},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - A PRACTICAL METHOD FOR SELF-ADAPTING GAUSSIAN EXPECTATION MAXIMIZATION
SN - 978-989-8425-00-3
AU - Greggio N.
AU - Bernardino A.
AU - Santos-Victor J.
PY - 2010
SP - 36
EP - 44
DO - 10.5220/0002894600360044