Conditions for non-negative independent component analysis

@misc{citeulike:2787415, abstract = {We consider the noiseless linear independent component analysis problem, in the case where the hidden sources s are non-negative. We assume that the random variables s i s are well-grounded in that they have a non-vanishing pdf in the (positive) neighbourhood of zero. For an orthonormal rotation y = Wx of pre-whitened observations x = QAs, under certain reasonable conditions we show that y is a permutation of the s (apart from a scaling factor) if and only if y is non-negative with...}, author = {Plumbley, M. }, citeulike-article-id = {2787415}, keywords = {ica, nmf}, posted-at = {2008-05-12 10:05:54}, priority = {2}, title = {Conditions for non-negative independent component analysis}, url = {http://citeseer.ist.psu.edu/531975.html}, year = {2002} }

TY - GEN ID - citeulike:2787415 L3 - citeulike-article-id:2787415 TI - Conditions for non-negative independent component analysis N2 - We consider the noiseless linear independent component analysis problem, in the case where the hidden sources s are non-negative. We assume that the random variables s i s are well-grounded in that they have a non-vanishing pdf in the (positive) neighbourhood of zero. For an orthonormal rotation y = Wx of pre-whitened observations x = QAs, under certain reasonable conditions we show that y is a permutation of the s (apart from a scaling factor) if and only if y is non-negative with... KW - ica KW - nmf AU - Plumbley, M PY - 2002/// UR - http://citeseer.ist.psu.edu/531975.html ER -