Advertisement

Robust Nonlinear Dimension Reduction: A Self-organizing Approach

  • Yuexian Hou
  • Liyue Yao
  • Pilian He
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3614)

Abstract

Most NDR algorithms need to solve large-scale eigenvalue problems or some variation of eigenvalue problems, which is of quadratic complexity of time and might be unpractical in case of large-size data sets. Besides, current algorithms are global, which are often sensitive to noise and disturbed by ill-conditioned matrix. In this paper, we propose a novel self-organizing NDR algorithm: SIE. The time complexity of SIE is O(NlogN). The main computing procedure of SIE is local, which improves the robustness of the algorithm remarkably.

Keywords

Anchor Point Geodesic Distance Noise Point Outer Cycle Swiss Data 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baum, E.: What Is Thought? MIT Press, Cambridge (2004)Google Scholar
  2. 2.
    Tenenbaum, J.B., et al.: Science, December 22, vol. 290 (2000)Google Scholar
  3. 3.
    Roweis, S.T., et al.: Science, December 22, vol. 290 (2000)Google Scholar
  4. 4.
    Belkin, M., et al.: NIPS (2001)Google Scholar
  5. 5.
    Donoho, D.L., et al.: PNAS, May 13, vol. 100(10) (2003)Google Scholar
  6. 6.
    Agrafiotis, D.K., et al.: A self-organizing principle for learning nonlinear manifolds. PNAS Early Edition. Google Scholar
  7. 7.
    Cormen, Leiserson, et al.: Introduction to Algorithms, 2nd edn. MIT press, Cambridge (2001)zbMATHGoogle Scholar
  8. 8.
    Yuexian, H., Zheng, D., Pilian, H.: Self-organizing Isometric Embedding. Computer research and development (2) (2005) (in Chinese)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Yuexian Hou
    • 1
  • Liyue Yao
    • 1
  • Pilian He
    • 1
  1. 1.School of Electronic Information EngineeringTianjin University

Personalised recommendations