Sciweavers

613 search results - page 20 / 123
» The Pre-Image Problem in Kernel Methods
Sort
View
ECML
2004
Springer
13 years 11 months ago
Efficient Hyperkernel Learning Using Second-Order Cone Programming
The kernel function plays a central role in kernel methods. Most existing methods can only adapt the kernel parameters or the kernel matrix based on empirical data. Recently, Ong e...
Ivor W. Tsang, James T. Kwok
SIGKDD
2000
139views more  SIGKDD 2000»
13 years 7 months ago
Support Vector Machines: Hype or Hallelujah?
Support Vector Machines (SVMs) and related kernel methods have become increasingly popular tools for data mining tasks such as classification, regression, and novelty detection. T...
Kristin P. Bennett, Colin Campbell
ICML
2005
IEEE
14 years 8 months ago
Predictive low-rank decomposition for kernel methods
Low-rank matrix decompositions are essential tools in the application of kernel methods to large-scale learning problems. These decompositions have generally been treated as black...
Francis R. Bach, Michael I. Jordan
KDD
2008
ACM
181views Data Mining» more  KDD 2008»
14 years 8 months ago
Learning subspace kernels for classification
Kernel methods have been applied successfully in many data mining tasks. Subspace kernel learning was recently proposed to discover an effective low-dimensional subspace of a kern...
Jianhui Chen, Shuiwang Ji, Betul Ceran, Qi Li, Min...
ICDM
2003
IEEE
153views Data Mining» more  ICDM 2003»
14 years 25 days ago
Dimensionality Reduction Using Kernel Pooled Local Discriminant Information
We study the use of kernel subspace methods for learning low-dimensional representations for classification. We propose a kernel pooled local discriminant subspace method and com...
Peng Zhang, Jing Peng, Carlotta Domeniconi