Sparse Coding Neural Gas for the Separation of Noisy Overcomplete Sources

Authors:
Kai Labusch;Erhardt Barth;Thomas Martinetz
Affiliations:
Institute for Neuro- and Bioinformatics, University of Lübeck, Lübeck, Germany 23538;Institute for Neuro- and Bioinformatics, University of Lübeck, Lübeck, Germany 23538;Institute for Neuro- and Bioinformatics, University of Lübeck, Lübeck, Germany 23538
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 4
Cited 1

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Atomic Decomposition by Basis Pursuit

SIAM Journal on Scientific Computing
Learning Overcomplete Representations

Neural Computation
Stable recovery of sparse overcomplete representations in the presence of noise

IEEE Transactions on Information Theory

Approaching the Time Dependent Cocktail Party Problem with Online Sparse Coding Neural Gas

WSOM '09 Proceedings of the 7th International Workshop on Advances in Self-Organizing Maps

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider the problem of separating noisy overcomplete sources from linear mixtures, i.e., we observe Nmixtures of M Nsparse sources. We show that the "Sparse Coding Neural Gas" (SCNG) algorithm [1] can be employed in order to estimate the mixing matrix. Based on the learned mixing matrix the sources are obtained by orthogonal matching pursuit. Using artificially generated data, we evaluate the influence of (i) the coherence of the mixing matrix, (ii) the noise level, and (iii) the sparseness of the sources with respect to the performance that can be achieved on the representation level. Our results show that if the coherence of the mixing matrix and the noise level are sufficiently small and the underlying sources are sufficiently sparse, the sources can be estimated from the observed mixtures.