TY - GEN
T1 - A fast training algorithm for least squares SVM
AU - Jiang, Shouda
AU - Lin, Lianlei
AU - Sun, Chao
PY - 2007
Y1 - 2007
N2 - A fast training algorithm for Least Squares SVM (LS-SVM) classifiers was proposed, which is based on incremental and decremental learning theory. When a SV (Support Vector) is added or removed, computation based on previous training result replaces large-scale matrix inverse, thus the computation cost is reduced. The innovation is that by reasonable use of incremental and decremental learning the proposed algorithm can adaptively adjust the size of training sets (number of SVs) according to the specific classification problem. Finally several experiments show the validity of proposed algorithm.
AB - A fast training algorithm for Least Squares SVM (LS-SVM) classifiers was proposed, which is based on incremental and decremental learning theory. When a SV (Support Vector) is added or removed, computation based on previous training result replaces large-scale matrix inverse, thus the computation cost is reduced. The innovation is that by reasonable use of incremental and decremental learning the proposed algorithm can adaptively adjust the size of training sets (number of SVs) according to the specific classification problem. Finally several experiments show the validity of proposed algorithm.
UR - https://www.scopus.com/pages/publications/47349130584
U2 - 10.1109/IIH-MSP.2007.18
DO - 10.1109/IIH-MSP.2007.18
M3 - 会议稿件
AN - SCOPUS:47349130584
SN - 0769529941
SN - 9780769529943
T3 - Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.
SP - 586
EP - 589
BT - Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.
T2 - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007
Y2 - 26 November 2007 through 28 November 2007
ER -