Kernelizing Vector Quantization Algorithms - CentraleSupélec Access content directly
Conference Papers Year : 2009

Kernelizing Vector Quantization Algorithms

Abstract

The kernel trick is a well known approach allowing to implicitly cast a linear method into a nonlinear one by replacing any dot product by a kernel function. However few vector quantization algorithms have been kernelized. Indeed, they usually imply to compute linear transformations (e.g. moving prototypes), what is not easily kernelizable. This paper introduces the Kernel-based Vector Quantization (KVQ) method which allows working in an approximation of the feature space, and thus kernelizing any Vector Quantization (VQ) algorithm.
Fichier principal
Vignette du fichier
es2009-49.pdf (668.71 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-00429892 , version 1 (04-12-2009)

Identifiers

  • HAL Id : hal-00429892 , version 1

Cite

Matthieu Geist, Olivier Pietquin, Gabriel Fricout. Kernelizing Vector Quantization Algorithms. ESANN'2009, Apr 2009, Bruges, Belgium. pp.541-546. ⟨hal-00429892⟩
55 View
105 Download

Share

Gmail Facebook X LinkedIn More