Density Kernels on Unordered Sets for Kernel-Based Signal Processing
Authors:
- 1 April 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15206149) , II-417-417
Abstract
Algorithms involved in applications such as speaker recognition or image classification need to be able to process data which are sets of vectors with variable size. As opposed to the standard setting for kernel methods, where the data are individual vectors, it is difficult to build a reliable reproducing kernel between such sets of unordered vectors. Most effective techniques rely on the design of kernel calculated on densities estimated independently on each set of vectors; however, this calculation can be numerically tricky: therefore these techniques either use poor estimates such as histograms, or assume unjustified restrictive conditions. In this paper, we improve on the existing framework and design kernels between densities, where these are estimated using an effective nonparametric technique, namely the Akaike-Parzen-Rosenblatt (APR) estimate. Closed-form expressions are obtained for positive definite kernels, and simulation results illustrate the soundness of the approach.Keywords
This publication has 7 references indexed in Scilit:
- Reproducing Kernel Hilbert Spaces in Probability and Statistics2004
- Optimized support vector machines for nonstationary signal classificationIEEE Signal Processing Letters, 2002
- A Global Geometric Framework for Nonlinear Dimensionality ReductionScience, 2000
- Functional Data Analysis1997
- Choice of Kernel Order in Density EstimationThe Annals of Statistics, 1988
- Density Estimation for Statistics and Data Analysis1986
- Algorithm AS 176: Kernel Density Estimation Using the Fast Fourier TransformJournal of the Royal Statistical Society Series C: Applied Statistics, 1982