| | |
Summary: Localized Multiple Kernel Regression
Mehmet G¨onen
Department of Computer Engineering
Bogazic¸i University, 34342, Istanbul, Turkey
gonen@boun.edu.tr
Ethem Alpaydin
Department of Computer Engineering
Bogazic¸i University, 34342, Istanbul, Turkey
alpaydin@boun.edu.tr
Abstract
Multiple kernel learning (MKL) uses a weighted
combination of kernels where the weight of each kernel
is optimized during training. However, MKL assigns
the same weight to a kernel over the whole input space.
Our main objective is the formulation of the localized
multiple kernel learning (LMKL) framework that al-
lows kernels to be combined with different weights in
different regions of the input space by using a gating
model. In this paper, we apply the LMKL framework to
regression estimation and derive a learning algorithm
|
