摘要
Vapnik等人提出基于统计学习理论的支持向量机(SVM,Support Vector Machices)算法,将其运用于模式识别中,取得了较好的效果。但传统的SVM算法针对不平衡样本集时,效果很不理想,很多的科研人员对该问题进行广泛而深入的研究,较为系统的回顾这一个研究分支在过去10年的发展动态。
Vapnick and his collaborators supposed the useful algorithm :Support Vectors Machines( SVMs ) based on statistical learning thorey. The algorithm has been applied to the field of pattern recognition and obtained outstanding results. The traditional SVMs doesn’t show distinguished outputs with the unbalanced data sets. Many scholars have done abroad and deep reaches on this problem to improve the performance of SVMs. The advances in such algorithm studies in the last ten years are reviewed in this paper.
出处
《计算机与数字工程》
2007年第10期21-23,69,共4页
Computer & Digital Engineering