Bayesian self-organization driven by prior probability distributions

Authors:
Alan L. Yuille;Stelios M. Smirnakis;Lei Xu
Affiliations:
Division of Applied Sciences, Harvard University, Cambridge, MA 02138, USA;Division of Applied Sciences, Harvard University, Cambridge, MA 02138, USA;Division of Applied Sciences, Harvard University, Cambridge, MA 02138, USA
Venue:
Neural Computation
Year:
1995

Citing 4
Cited 2

Computational vision and regularization theory

Nature
Approximation capabilities of multilayer feedforward networks

Neural Networks
Data Fusion for Sensory Information Processing Systems

Data Fusion for Sensory Information Processing Systems
Towards a theory of early visual processing

Neural Computation

Adaptive calibration of imaging array detectors

Neural Computation
Attractor memory with self-organizing input

BioADIT'06 Proceedings of the Second international conference on Biologically Inspired Approaches to Advanced Information Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recent work by Becker and Hinton (1992) shows a promising mechanism, based on maximizing mutual information assuming spatial coherence, by which a system can self-organize 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 theories of visual perception and to other organization principles for early vision (Atick and Redlich 1990). Methods for implementation using variants of stochastic learning are described.