Post Nonlinear Independent Subspace Analysis

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4668)


In this paper a generalization of Post Nonlinear Independent Component Analysis (PNL-ICA) to Post Nonlinear Independent Subspace Analysis (PNL-ISA) is presented. In this framework sources to be identified can be multidimensional as well. For this generalization we prove a separability theorem: the ambiguities of this problem are essentially the same as for the linear Independent Subspace Analysis (ISA). By applying this result we derive an algorithm using the mirror structure of the mixing system. Numerical simulations are presented to illustrate the efficiency of the algorithm.


Independent Component Analysis Independent Component Analysis Iterate Function System Machine Learn Research Linear 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.
    Cichocki, A., Amari, S.: Adaptive blind signal and image processing. John Wiley & Sons, West Sussex, England (2002)Google Scholar
  2. 2.
    Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, West Sussex, England (2001)Google Scholar
  3. 3.
    Taleb, A., Jutten, C.: Source separation in post-nonlinear mixtures. IEEE Transactions on Signal Processing 10(47), 2807–2820 (1999)CrossRefGoogle Scholar
  4. 4.
    Jutten, C., Karhunen, J.: Advances in blind source separation (BSS) and independent component analysis (ICA) for nonlinear systems. International Journal of Neural Systems 14(5), 267–292 (2004)CrossRefGoogle Scholar
  5. 5.
    Cardoso, J.: Multidimensional independent component analysis. In: Proc. of ICASSP 1998, vol. 4, pp. 1941–1944 (1998)Google Scholar
  6. 6.
    Akaho, S., Kiuchi, Y., Umeyama, S.: MICA: Multimodal independent component analysis. In: Proc. of IJCNN 1999, vol. 2, pp. 927–932 (1999)Google Scholar
  7. 7.
    Hyvärinen, A., Hoyer, P.O.: Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces. Neural Computation 12, 1705–1720 (2000)CrossRefGoogle Scholar
  8. 8.
    Hyvärinen, A., Köster, U.: FastISA: A fast fixed-point algorithm for independent subspace analysis. In: Proc. of ESANN, pp. 371–376 (2006)Google Scholar
  9. 9.
    Vollgraf, R., Obermayer, K.: Multi-dimensional ICA to separate correlated sources. In: Proc. of NIPS 2001, vol. 14, pp. 993–1000 (2001)Google Scholar
  10. 10.
    Bach, F.R., Jordan, M.I.: Beyond independent components: Trees and clusters. Journal of Machine Learning Research 4, 1205–1233 (2003)CrossRefGoogle Scholar
  11. 11.
    Póczos, B., Lőrincz, A.: Independent subspace analysis using k-nearest neighborhood distances. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 163–168. Springer, Heidelberg (2005)Google Scholar
  12. 12.
    Póczos, B., Lőrincz, A.: Independent subspace analysis using geodesic spanning trees. In: Proc. of ICML 2005, vol. 119, pp. 673–680 (2005)Google Scholar
  13. 13.
    Theis, F.J.: Blind signal separation into groups of dependent signals using joint block diagonalization. In: Proc. of ISCAS 2005, vol. 6, pp. 5878–5881 (2005)Google Scholar
  14. 14.
    Szabó, Z., Lőrincz, A.: Real and complex independent subspace analysis by generalized variance. In: Proc. of ICARN, pp. 85–88 (2006)Google Scholar
  15. 15.
    Nolte, G., Meinecke, F.C., Ziehe, A., Müller, K.-R.: Identifying interactions in mixed and noisy complex systems. Physical Review E 73(051913) (2006)Google Scholar
  16. 16.
    Theis, F.J.: Towards a general independent subspace analysis. In: Proc. of NIPS, vol. 19 (2006)Google Scholar
  17. 17.
    Comon, P.: Independent component analysis, a new concept? Signal Processing 36, 287–314 (1994)zbMATHCrossRefGoogle Scholar
  18. 18.
    Achard, S., Jutten, C.: Identifiability of post nonlinear mixtures. IEEE Signal Processing Letters 12(5), 423–426 (2005)CrossRefGoogle Scholar
  19. 19.
    Theis, F.J.: Uniqueness of complex and multidimensional independent component analysis. Signal Processing 84(5), 951–956 (2004)CrossRefGoogle Scholar
  20. 20.
    Theis, F.J.: A new concept for separability problems in source separation. Neural Computation 16, 1827–1850 (2004)zbMATHCrossRefGoogle Scholar
  21. 21.
    Theis, F.J.: Multidimensional independent component analysis using characteristic functions. In: Proc. of EUSIPCO (2005)Google Scholar
  22. 22.
    Petrov, V.: Central limit theorem for m-dependent variables. In: Proc. of the All-Union Conf. on Probability Theory and Mathematical Statistics, pp. 38–44 (1958)Google Scholar
  23. 23.
    Ziehe, A., Kawanabe, M., Harmeling, S., Müller, K.-R.: Blind separation of post-nonlinear mixtures using linearizing transformations and temporal decorrelation. Journal of Machine Learning Research 4(7-8), 1319–1338 (2004)CrossRefGoogle Scholar
  24. 24.
    Solé-Casals, J., Jutten, C., Pham, D.: Fast approximation of nonlinearities for improving inversion algorithms of PNL mixtures and wiener systems. Signal Processing 85, 1780–1786 (2005)CrossRefGoogle Scholar
  25. 25.
    Amari, S., Cichocki, A., Yang, H.H.: A new learning algorithm for blind signal separation. Advances in Neural Information Processing Systems 8, 757–763 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  1. 1.Department of Information Systems, Eötvös Loránd University, Pázmány P. sétány 1/C, Budapest H-1117Hungary

Personalised recommendations