发明申请
- 专利标题： Pre-processed feature ranking for a support vector machine
- 专利标题（中）： 支持向量机的预处理功能排名
-
申请号： US10494876申请日： 2002-11-07
-
公开(公告)号： US20050131847A1公开(公告)日： 2005-06-16
- 发明人: Jason Weston , Andre Elisseeff , Bernhard Scholkopf , Fernando Perez-Cruz , Isabelle Guyon
- 申请人： Jason Weston , Andre Elisseeff , Bernhard Scholkopf , Fernando Perez-Cruz , Isabelle Guyon
- 国际申请： PCT/US02/35576 WO 20021107
- 主分类号： G06F15/18
- IPC分类号： G06F15/18 ; G06G7/00 ; G06K9/62
摘要：
Features are preprocessed (204) to minimize classification error in a Support Vector Machines (200) used to identify patterns in large databases. Pre-processing (204) is performed to constrain features used to train (210) the SVM learning machine. Live data (226) is collected and processed (232) with SVM.
公开/授权文献
- US07475048B2 Pre-processed feature ranking for a support vector machine 公开/授权日：2009-01-06
信息查询
