@inproceedings{62e3f11a9f3949888a8a505c2c633ef4,
title = "Speeding up support vector machines: Probabilistic versus nearest neighbour methods for condensing training data",
abstract = "Several methods for reducing the running time of support vector machines (SVMs) are compared in terms of speed-up factor and classification accuracy using seven large real world datasets obtained from the UCI Machine Learning Repository. All the methods tested are based on reducing the size of the training data that is then fed to the SVM. Two probabilistic methods are investigated that run in linear time with respect to the size of the training data: blind random sampling and a new method for guided random sampling (Gaussian Condensing). These methods are compared with k-Nearest Neighbour methods for reducing the size of the training set and for smoothing the decision boundary. For all the datasets tested blind random sampling gave the best results for speeding up SVMs without significantly sacrificing classification accuracy.",
keywords = "Blind random sampling, Data mining, Gaussian condensing, Guided random sampling, K-nearest neighbour methods, Machine learning, SMO, Support vector machines, Training data condensation, Wilson editing",
author = "Mo{\"i}ri Gamboni and Abhijai Garg and Oleg Grishin and Oh, {Seung Man} and Francis Sowani and Anthony Spalvieri-Kruse and Toussaint, {Godfried T.} and Lingliang Zhang",
year = "2014",
doi = "10.5220/0004927003640371",
language = "English (US)",
isbn = "9789897580185",
series = "ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods",
publisher = "SciTePress",
pages = "364--371",
booktitle = "ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods",
note = "3rd International Conference on Pattern Recognition Applications and Methods, ICPRAM 2014 ; Conference date: 06-03-2014 Through 08-03-2014",
}