Independent component analysis, a new concept?
Signal Processing - Special issue on higher order statistics
Learning linear, sparse, factorial codes
Learning linear, sparse, factorial codes
Learning Overcomplete Representations
Neural Computation
Hi-index | 0.00 |
We present an independent component analysis (ICA) algorithm based on geometric considerations [10] [11] to decompose a linear mixture of more sources than sensor signals. Bofill and Zibulevsky [2] recently proposed a two-step approach for the separation: first learn the mixing matrix, then recover the sources using a maximum-likelihood approach. We present an efficient method for the matrix-recovery step mimicking the standard geometric algorithm thus generalizing Bofill and Zibulevsky's method.