A binary factorial code is a transformation that maps the input space into a binary string with independent bits. We apply independent component analysis, formulated as a density search, to the pursuit of such a code by considering a set of desired output bi-modal density functions. The idea is tested on a real image with the coder used also in a reversed order as a generative model. The results are also compared to a principal component analyzer. Fantasy blocks of the image transforms provide interesting clues on the nature of the learned representations. A binary factorial code i a transformation that maps the input space into a binary string with independent bits. We apply independent component analysis, formulated as a destiny search, to the pursuit of such a code by considering a set of desired output bi-modal density functions. The idea is tested on a real image with the coder used also in a reversed order as a generative model. The results are also compared to a principal component analyzer. Fantasy blocks of the image transforms provide interesting clues on the nature of the learned representations.
Searching for a Binary Factorial Code Using the ICA Framework
BUDILLON, Alessandra;
1998-01-01
Abstract
A binary factorial code is a transformation that maps the input space into a binary string with independent bits. We apply independent component analysis, formulated as a density search, to the pursuit of such a code by considering a set of desired output bi-modal density functions. The idea is tested on a real image with the coder used also in a reversed order as a generative model. The results are also compared to a principal component analyzer. Fantasy blocks of the image transforms provide interesting clues on the nature of the learned representations. A binary factorial code i a transformation that maps the input space into a binary string with independent bits. We apply independent component analysis, formulated as a destiny search, to the pursuit of such a code by considering a set of desired output bi-modal density functions. The idea is tested on a real image with the coder used also in a reversed order as a generative model. The results are also compared to a principal component analyzer. Fantasy blocks of the image transforms provide interesting clues on the nature of the learned representations.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.