SVM Training Time Reduction using Vector Quantization

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Gilles Lebrun Articles by Christophe Charrier Articles by Hubert Cardot

17th International Conference on Pattern Recognition (ICPR'04) - Volume 1

Cambridge UK

August 23-August 26

ISBN: 0-7695-2128-2

	ASCII Text	x
	Gilles Lebrun, Christophe Charrier, Hubert Cardot, "SVM Training Time Reduction using Vector Quantization," Pattern Recognition, International Conference on, vol. 1, pp. 160-163, 17th International Conference on Pattern Recognition (ICPR'04) - Volume 1, 2004.

	BibTex	x
	@article{ 10.1109/ICPR.2004.1334035, author = {Gilles Lebrun and Christophe Charrier and Hubert Cardot}, title = {SVM Training Time Reduction using Vector Quantization}, journal ={Pattern Recognition, International Conference on}, volume = {1}, year = {2004}, issn = {1051-4651}, pages = {160-163}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICPR.2004.1334035}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Pattern Recognition, International Conference on TI - SVM Training Time Reduction using Vector Quantization SN - 1051-4651 SP160 EP163 A1 - Gilles Lebrun, A1 - Christophe Charrier, A1 - Hubert Cardot, PY - 2004 KW - null VL - 1 JA - Pattern Recognition, International Conference on ER -

Gilles Lebrun, groupe Vision et Analyse d'Image, France

Christophe Charrier, groupe Vision et Analyse d'Image, France

Hubert Cardot, groupe Vision et Analyse d'Image, France

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICPR.2004.1334035

In this paper, we describe a new method for training SVM on large data sets. Vector Quantization is applied to reduce a large data set by replacing examples by prototypes. Training time for choosing optimal parameters is greatly reduced. Some experimental results yields to demonstrate that this method can reduce training time by a factor of 100, while preserving classification rate. Moreover this method allows to find a decision function with a low complexity when the training data set includes noisy or error examples.

Citation:

Gilles Lebrun, Christophe Charrier, Hubert Cardot, "SVM Training Time Reduction using Vector Quantization," icpr, vol. 1, pp.160-163, 17th International Conference on Pattern Recognition (ICPR'04) - Volume 1, 2004

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.