Skip to main content
Springer Nature Link
Log in

Gaussianizing Transformations for ICA

  • Conference paper
  • First Online:
Independent Component Analysis and Blind Signal Separation (ICA 2004)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 3195))

  • 1900 Accesses

Abstract

Nonlinear principal components analysis is shown to generate some of the most common criteria for solving the linear independent components analysis problem. These include minimum kurtosis, maximum likelihood and the contrast score functions. In this paper, a topology that can separate the independent sources from a linear mixture by specifically utilizing a Gaussianizing nonlinearity is demonstrated. The link between the proposed topology and nonlinear principal components is established. Possible extensions to nonlinear mixtures and several implementation issues are also discussed.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Hyvarinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. Wiley, New York (2001)

    Book  Google Scholar 

  2. Cichocki, A., Amari, S.I.: Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications. Wiley, New York (2002)

    Book  Google Scholar 

  3. Lee, T.W.: Independent Component Analysis: Theory and Applications. Kluwer, New York (1998)

    Book  Google Scholar 

  4. Hyvarinen, A.: Survey on Independent Component Analysis. Neural Computing Surveys 2, 94–128 (1999)

    Google Scholar 

  5. Jutten, C., Karhunen, J.: Advances in Nonlinear Blind Source Separation. In: Proceedings of ICA 2003, Nara, Japan, pp. 245–256 (2003)

    Google Scholar 

  6. Karhunen, J., Joutsensalo, J.: Representation ans Separation of Signals Using Nonlinear PCA Type Learning. Neural Networks 7, 113–127 (1994)

    Article  Google Scholar 

  7. Cardoso, J.F., Souloumiac, A.: Blind Beamforming for Non-Gaussian Signals. In: IEE Proceedings F: Radar and Signal Processing, vol. 140, pp. 362–370 (1993)

    Google Scholar 

  8. Papoulis, A.: Probability, Random Variables, and Stochastic Processes, 3rd edn. McGraw-Hill, New York (1991)

    MATH  Google Scholar 

  9. Chen, S., Gopinath, R.A.: Gaussianization. In: Proceedings of NIPS 2001, pp. 423–429. Denver, Colorado (2001)

    Google Scholar 

  10. Hyvarinen, A., Pajunen, P.: Nonlinear Independent Component Analysis: Existence and Uniqueness Results. Neural Networks 12, 429–439 (1999)

    Article  Google Scholar 

  11. Fiori, S.: A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold. Neural Computation 13, 1625–1647 (2001)

    Article  Google Scholar 

  12. Xu, L.: Least Mean Square Error Reconstruction Principle for Self-Organizing Neural Nets. Neural Networks 6, 627–648 (1993)

    Article  Google Scholar 

  13. Ziehe, A., Kawanabe, M., Harmeling, S., Muller, K.R.: Blind Separation of Post-nonlinear Mixtures Using Linearizing Transformations and Temporal Decorrelation. Journal of Machine Learning Research 4, 1319–1338 (2003)

    MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. CNEL, Electrical and Computer Engineering Department, University of Florida, Gainesville, Florida, 32611, USA

    Deniz Erdogmus, Yadunandana N. Rao & José Carlos Príncipe

Authors
  1. Deniz Erdogmus
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yadunandana N. Rao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. José Carlos Príncipe
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Dept. of Architecture and Computer Technology, University of Granada, Spain

    Carlos G. Puntonet  & Alberto Prieto  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Erdogmus, D., Rao, Y.N., Príncipe, J.C. (2004). Gaussianizing Transformations for ICA. In: Puntonet, C.G., Prieto, A. (eds) Independent Component Analysis and Blind Signal Separation. ICA 2004. Lecture Notes in Computer Science, vol 3195. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30110-3_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-30110-3_4

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-23056-4

  • Online ISBN: 978-3-540-30110-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics