Fast nonlinear dimensionality reduction with topology preserving networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2002

Fast nonlinear dimensionality reduction with topology preserving networks

Jakob Verbeek
Nikos Vlassis
  • Function : Author
  • PersonId : 853678

Abstract

We present a fast alternative for the Isomap algorithm. A set of quantizers is fit to the data and a neighborhood structure based on the competitive Hebbian rule is imposed on it. This structure is used to obtain low-dimensional description of the data by means of computing geodesic distances and multi dimensional scaling. The quantization allows for faster processing of the data. The speed-up as compared to Isomap is roughly quadratic in the ratio between the number of quan- tizers and the number of data points. The quantizers and neighborhood structure are use to map the data to the low dimensional space.
Fichier principal
Vignette du fichier
verbeek02esann.pdf (129.28 Ko) Télécharger le fichier
Vignette du fichier
VVK02b.png (17.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Loading...

Dates and versions

inria-00321500 , version 1 (16-02-2011)

Identifiers

  • HAL Id : inria-00321500 , version 1

Cite

Jakob Verbeek, Nikos Vlassis, Ben Krose. Fast nonlinear dimensionality reduction with topology preserving networks. 10th Eurorean Symposium on Artificial Neural Networks (ESANN '02), Apr 2002, Bruges, Belgium. ⟨inria-00321500⟩
100 View
210 Download

Share

Gmail Facebook X LinkedIn More