Learning Theory for Kernel and Metric Learning
主 题: Learning Theory for Kernel and Metric Learning
报告人: Prof. Yiming Ying (University of Exeter, UK)
时 间: 2012-10-16 15:00-16:00
地 点: 理科一号楼1560
The performance of many machine learning algorithms largely depends on the data representation via the choice of kernel function or distance metric. Hence, one central issue is the problem of learning a kernel and metric from data. In this talk, I will present our work on theoretical
