Sensitivity to parameter and data variations in dimensionality reduction techniques

Garcia Fernandez, Francisco J.;Verleysen, Michel;Lee, John;Diaz, Ignacio
(2013) 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2013) — Location: Bruges (Belgium) (24.April.2013)

Files

Sensitivitytoparameteranddatavariationsindimensionalityreductiontechniques.pdf
  • Restricted Access
  • Adobe PDF
  • 1.71 MB
Request a copy

Details

Authors
  • Garcia Fernandez, Francisco J.University of Oviedo, Italy
    Author
  • Verleysen, MichelUCLouvain
    Author
  • Lee, Johnorcid-logoUCLouvain
    Author
  • Diaz, IgnacioUniversity of Oviedo, Italy
    Author
Abstract
Dimensionality reduction techniques aim at representing high dimensional data in a meaningful and lower-dimensional space, improving the human comprehension and interpretation of data. In recent years, newer nonlinear techniques have been proposed in order to address the limitation of linear techniques. This paper presents a study of the stability of some of these dimensionality reduction techniques, analyzing their behavior under changes in the parameters and the data. The performances of these techniques are investigated on artificial datasets. The paper presents these results by identifying the weaknesses of each technique, and suggests some data-processing tasks to improve the stability.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Garcia Fernandez, F. J., Verleysen, M., Lee, J., & Diaz, I. (2013). Sensitivity to parameter and data variations in dimensionality reduction techniques. Proceedings of the 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2013), p. 95-100. https://hdl.handle.net/2078.5/253754