Paper No: 70
Learning of translation-invariant independent components: Multivariate anechoic Mixtures
Author(s): Lars Omlor, Martin A. Giese
Abstract
For the extraction of sources with unsupervised learning techniques invariance
under certain transformations, such as shifts, rotations or scaling, is often
a desirable property. A straight-forward approach for accomplishing this
goal is to include these transformations and its parameters into the mixing
model. For the case of one-dimensional signals in presence of shifts this
problem has been termed anechoic demixing, and several algorithms for the
analysis of time series have been proposed. Here, we generalize this approach
for sources depending on multidimensional
arguments and apply it for learning of translation-invariant features from higher-dimensional
data, such as images. A new algorithm for the solution of such high-dimensional
anechoic demixing problems based on the Wigner-Ville distribution is presented.
It solves the multidimensional problem by projection onto multiple one-dimensional
problems.
The feasibility of this algorithm is demonstrated by learning independent
features from sets of real images |
