The Projection Adaptive Natural Gradient Online Algorithm for SVM

摘要：

The training of Support Vector Machine (SVM) is an optimization problem of quadratic programming which can not be applied to the online training in real time applications or time-variant data source. The online algorithms proposed by other researchers have high computational complexity and slow training speed. In this paper the projection gradient and adaptive natural gradient is combined. The projection adaptive natural gradient online algorithm is proposed. The learning performance is compared via prediction of the concentration of component A of Continuous Stirred Tank Reactor. The results of simulation demonstrate that the time taken by the projection adaptive natural gradient online algorithm is much less than that of incremental algorithm, while keep similar prediction precision.

关键词： Natural Gradient Online Algorithm Projection

作者: SUN Zonghai SHI Buhai

作者单位: College of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, P. R. China

会议类型: 国际会议

会议名称: The 29th Chinese Control Conference(第二十九届中国控制会议)

会议地点: 北京

会议语种:英文

页码: 1-5

在线出版日期: 2010-07-29（万方平台首次上网日期，不代表论文的发表时间）