Self-Organizing Sparse Codes

Sparse coding as applied to natural image patches learns Gabor-like components that resemble those found in the lower areas of the visual cortex. This biological motivation for sparse coding would also suggest that the learned receptive field elements be organized spatially by their response properties. However, the factorized prior in the original sparse coding model does not enforce this. We investigate ways of enforcing a topography over the learned codes in a locally self-organizing map approach.