Share Email Print

Proceedings Paper

Propagation Of Uncertainty Using Neural Networks
Author(s): Raghu J. Krishnapuram; Joonwhoan Lee
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Uncertainty management (belief maintenance) is an important part of most knowledge-based computer vision systems. In this paper, we examine a methodology to aggregate and propagate uncertainties in a neural-network-like structure. Each node in the network represents a hypothesis. The inputs are the uncertainties associated with the knowledge sources that support the hypothesis, and the output is the aggregated uncertainty. The activation function is selected based on concepts from fuzzy set theory. The parameters of the activation function are chosen depending on the type of aggregation required. In addition to the traditional union and intersection aggregation connectives, we propose the use of a generalized mean connective to increase flexibility. Some attractive properties of the connectives are discussed and a training procedure for such networks is also proposed.

Paper Details

Date Published: 27 March 1989
PDF: 7 pages
Proc. SPIE 1002, Intelligent Robots and Computer Vision VII, (27 March 1989); doi: 10.1117/12.960298
Show Author Affiliations
Raghu J. Krishnapuram, University of Missouri (United States)
Joonwhoan Lee, University of Missouri (United States)

Published in SPIE Proceedings Vol. 1002:
Intelligent Robots and Computer Vision VII
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top