Learning with Transformation Invariant Kernels
Walder, Christian, Chapelle, Olivier
–Neural Information Processing Systems
This paper considers kernels invariant to translation, rotation and dilation. We show that no nontrivial positive definite (p.d.) kernels exist which are radial and dilation invariant, only conditionally positive definite (c.p.d.) ones. Accordingly, we discuss the c.p.d.
Neural Information Processing Systems
Dec-31-2008