Title :
A Algorithm to Incremental Learning with Support Vector Machine and Its Application in Multi-class Classification
Author :
Zhao Ying ; Wan Fuyong
Author_Institution :
Dept. of Math., East China Normal Univ., Shanghai, China
Abstract :
Support vector machine (SVM) is a new statistical learning method. By analyzing the theory and characteristics of SVM, this paper presents an algorithm of incremental learning. This algorithm is tested with multi-class classification and results show that this algorithm reduces the training time. Meanwhile, it keeps the testing accuracy.
Keywords :
learning (artificial intelligence); pattern classification; support vector machines; incremental learning; multiclass classification; statistical learning; support vector machine; Algorithm design and analysis; Electronic mail; IEEE catalog; Machine learning; Mathematics; Mercury (metals); Statistical learning; Support vector machine classification; Support vector machines; Testing; Incremental Learning; Multi-class Classification; Support Vector Machine (SVM);
Conference_Titel :
Control Conference, 2006. CCC 2006. Chinese
Conference_Location :
Harbin
Print_ISBN :
7-81077-802-1
DOI :
10.1109/CHICC.2006.280868
