Recent work by Becker and Hinton (1992) shows a promising mechanism, b
ased on maximizing mutual information assuming spatial coherence, by w
hich a system can self-organize to learn visual abilities such as bino
cular stereo. We introduce a more general criterion, based on Bayesian
probability theory, and thereby demonstrate a connection to Bayesian
theories of visual perception and to other organization principles for
early vision (Atick and Redlich 1990). Methods for implementation usi
ng variants of stochastic learning are described.