License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-20356
URL: http://drops.dagstuhl.de/opus/volltexte/2009/2035/
Go to the corresponding Portal

de Vries, Gert-Jan ; Biehl, Michael

Analysis of Robust Soft Learning Vector Quantization and an application to Facial Expression Recognition

pdf-format:
Document 1.pdf (167 KB)

Abstract

Learning Vector Quantization (LVQ) is a popular method for multiclass classification. Several variants of LVQ have been developed recently, of which Robust Soft Learning Vector Quantization (RSLVQ) is a promising one. Although LVQ methods have an intuitive design with clear updating rules, their dynamics are not yet well understood. In simulations within a controlled environment RSLVQ performed very close to optimal. This controlled environment enabled us to perform a mathematical analysis as a first step in obtaining a better theoretical understanding of the learning dynamics. In this talk I will discuss the theoretical analysis and its results. Moreover, I will focus on the practical application of RSLVQ to a real world dataset containing extracted features from facial expression data.

BibTeX - Entry

@InProceedings{devries_et_al:DSP:2009:2035,
  author =	{Gert-Jan de Vries and Michael Biehl},
  title =	{Analysis of Robust Soft Learning Vector Quantization and an application to Facial Expression Recognition},
  booktitle =	{Similarity-based learning on structures},
  year =	{2009},
  editor =	{Michael Biehl and Barbara Hammer and Sepp Hochreiter and Stefan C. Kremer and Thomas Villmann},
  number =	{09081},
  series =	{Dagstuhl Seminar Proceedings},
  ISSN =	{1862-4405},
  publisher =	{Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2009/2035},
  annote =	{Keywords: Learning Vector Quantization, Analysis, Facial Expression Recognition}
}

Keywords: Learning Vector Quantization, Analysis, Facial Expression Recognition
Seminar: 09081 - Similarity-based learning on structures
Issue Date: 2009
Date of publication: 23.06.2009

DROPS-Home | Fulltext Search | Imprint Published by LZI