An ICA Learning Algorithm Utilizing Geodesic Approach

  • Tao Yu
  • Huai-Zong Shao
  • Qi-Cong Peng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3971)


This paper presents a novel independent component analysis algorithm that separates mixtures using serially updating geodesic method. The geodesic method is derived from the Stiefel manifold, and an on-line version of this method that can directly treat with the unwhitened observations is obtained. Simulation of artificial data as well as real biological data reveals that our proposed method has fast convergence.


Independent Component Analysis Blind Source Separation Geodesic Flow Independent Component Analysis Algorithm Instantaneous Mixture 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Jutten, C., Herault, J.: Blind Separation of Sources: An Adaptive Algorithm Based on Neuromimetic Architecture. Signal Processing 24, 1–10 (1991)MATHCrossRefGoogle Scholar
  2. 2.
    Hyvarinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. Wiley, New York (2001)CrossRefGoogle Scholar
  3. 3.
    Douglas, C.: Self-stabilized Gradient Algorithms for Blind Source Separation with Orthogonality Constrains. IEEE Transactions on Signal Processing 11, 1490–1497 (2000)Google Scholar
  4. 4.
    Manton, H.: Optimization Algorithms Exploiting Unitary Constrains. IEEE Tran. on Signal Processing 50, 635–650 (2002)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Edelman, A., Arias, T., Smith, S.T.: The Geometry of Algorithms with Orthogonality Constraints. J. Matrix Anal. Appl. 20, 783–787 (1998)Google Scholar
  6. 6.
    Douglas, C., Amari, S.: Natural Gradient Adaptation in Unsupervised Adaptive Filtering. In: Haykin, S. (ed.) Blind Source Separation, pp. 13–61. Wiley, New York (2000)Google Scholar
  7. 7.
    Fiori, S.: Qusi-geodesic Neural Learning Algorithms Over the Orthogonal Group: A Tutorial. Journal of Machine Learning Research 1, 1–42 (2005)Google Scholar
  8. 8.
    Edelman, A., Arias, T.A., Smith, S.T.: The Geometry of Algorithms with Orthogonality Constraints. Matrix Anal. Applicant. 20, 303–353 (1998)MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Plumbley, D.: Algorithms for Nonnegative Independent Component Analysis. IEEE Transactions on Neural Networks 14, 534–543 (2003)CrossRefGoogle Scholar
  10. 10.
    Nishimori, Y.: Learning Algorithm for ICA by Geodesic Flows on Orthogonal Group. In: PIJC Neural Networks, Washington, DC, vol. 2, pp. 933–988 (1999)Google Scholar
  11. 11.
    Nishimori, Y., Akaho, S.: Learning Algorithms Utilizing Quasi-geodesic Flows on the Stiefel Manifold. Neurocomputing 67, 106–135 (2005)CrossRefGoogle Scholar
  12. 12.
    Cardoso, L.: Equivariant Aadaptive Source Separation. IEEE Trans. on Signal Processing 44, 3017–3030 (1996)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Choi, S., Cichocki, A., Amari, S.: Flexible Independent Component Analysis. Neural Networks for Signal Processing VIII, 83–92 (1998)Google Scholar
  14. 14.
    Girolami, M.: Self-Organising Neural Networks. Independent Component Analysis and Blind Source Separation. Springer, London (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tao Yu
    • 1
    • 2
  • Huai-Zong Shao
    • 1
  • Qi-Cong Peng
    • 1
  1. 1.UESTC-Texas Instrument DSPs LaboratoryUniversity of Electronic Science and Technology of ChinaChengduChina
  2. 2.Blind Source Separation Research GroupUniversity of Electronic Science and Technology of ChinaChengduChina

Personalised recommendations