Bayesian Self-Organization
Abstract
Recent work by Becker and Hinton (Becker and Hinton, 1992) shows a promising mechanism, based on maximizing mutual in(cid:173) formation assuming spatial coherence, by which a system can self(cid:173) organize itself to learn visual abilities such as binocular stereo. We introduce a more general criterion, based on Bayesian probability theory, and thereby demonstrate a connection to Bayesian theo(cid:173) ries of visual perception and to other organization principles for early vision (Atick and Redlich, 1990). Methods for implementa(cid:173) tion using variants of stochastic learning are described and, for the special case of linear filtering, we derive an analytic expression for the output.
Cite
Text
Yuille et al. "Bayesian Self-Organization." Neural Information Processing Systems, 1993.Markdown
[Yuille et al. "Bayesian Self-Organization." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/yuille1993neurips-bayesian/)BibTeX
@inproceedings{yuille1993neurips-bayesian,
title = {{Bayesian Self-Organization}},
author = {Yuille, Alan L. and Smirnakis, Stelios M. and Xu, Lei},
booktitle = {Neural Information Processing Systems},
year = {1993},
pages = {1001-1008},
url = {https://mlanthology.org/neurips/1993/yuille1993neurips-bayesian/}
}