Chinese Journal of Computers   Full Text
Title	A Learning Strategy of SVM Used to Large Training Set
Authors	LI Hong-Lian1),4) WANG Chun-Hua2) YUAN Bao-Zong1) ZHU Zhan-Hui3)
Address	1)（Institute of Information Science, Beijing Jiaotong University, Beijing 100044) 2)(Beijing Samsung Communication Technology Research Institute, Beijing 100081) 3)(Hebei Construction Group Company Limited, Baoding 071000）
Year	2004
Issue	No.5(715-719)
Abstract &   Background	This paper proposes a learning strategy of SVM used to large training set. First authors train an initial classifier with a small training set, then prune the large training set with the initial classifier to obtain a small reduction set. Training with the reduction set, final classifier is obtained. Experiments show that the learning strategy not only reduces the cost greatly but also obtains a classifier that has the same accuracy as（even better than） the classifier obtained by training large set directly. In addition, speed of classification is greatly improved. keywords support vector machines; pruning; large training set