Searching for a binary factorial code using the ICA framework

A binary factorial code is a transformation that maps the input space into a binary string with independent bits. We apply independent component analy sis, formulated as a density search, to the pursuit of such a code by consi dering a set of desired output bi-modal density functions. The idea is test ed on a real image with the coder used also in a reversed order as a genera tive model. The results are also compared to a principal component analyzer . Fantasy blocks of the image transforms provide interesting clues on the n ature of the learned representations. (C) 1998 Elsevier Science B.V. All ri ghts reserved.