Blind Source Separation and Deconvolution: The Dynamic Component Analysis Algorithm

  title={Blind Source Separation and Deconvolution: The Dynamic Component Analysis Algorithm},
  author={Hagai Attias and Christoph E. Schreiner},
  journal={Neural Computation},
We derive a novel family of unsupervised learning algorithms for blind separation of mixed and convolved sources. Our approach is based on formulating the separation problem as a learning task of a spatiotemporal generative model, whose parameters are adapted iteratively to minimize suitable error functions, thus ensuring stability of the algorithms. The resulting learning rules achieve separation by exploiting high-order spatiotemporal statistics of the mixture data. Different rules are… CONTINUE READING
Highly Influential
This paper has highly influenced 10 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
97 Citations
35 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 97 extracted citations


Publications referenced by this paper.
Showing 1-10 of 35 references

Multichannel blind deconvolution: FIR matrix algebra and separation of multipath mixtures

  • R. Lambert
  • Unpublished doctoral dissertation,
  • 1996
Highly Influential
1 Excerpt

Similar Papers

Loading similar papers…