A randomly perturbed infomax algorithm for blind source separation

@article{He2013ARP,
  title={A randomly perturbed infomax algorithm for blind source separation},
  author={Qi He and Jack Xin},
  journal={2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2013},
  pages={3218-3222}
}
We present a novel modification to the well-known infomax algorithm of blind source separation. Under natural gradient descent, the infomax algorithm converges to a stationary point of a limiting ordinary differential equation. However, due to the presence of saddle points or local minima of the corresponding likelihood function, the algorithm may be trapped around these “bad” stationary points for a long time, especially if the initial data are near them. To speed up convergence, we propose to… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES

Spurious Solution of the Maximum Likelihood Approach to ICA

  • IEEE Signal Processing Letters
  • 2010
VIEW 1 EXCERPT

Scaled Natural Gradient Algorithms for Instantaneous and Convolutive Blind Source Separation

  • 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
  • 2007
VIEW 1 EXCERPT

On the convergence of blind separation and deconvolution

T. P. von Hoff
  • Ph.D. thesis,
  • 2000
VIEW 1 EXCERPT

On the stability of source separation algorithms

J. F. Cardoso
  • The Journal of VLSI Signal Processing, vol. 26, no. 1, pp. 7–14, 2000.
  • 2000
VIEW 2 EXCERPTS

Separation of two independent sources by the information-theoretic approach with cubic nonlinearity

  • Proceedings of International Conference on Neural Networks (ICNN'97)
  • 1997
VIEW 2 EXCERPTS