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.
Raghu J. Krishnapuram,
"Propagation Of Uncertainty Using Neural Networks", Proc. SPIE 1002, Intelligent Robots and Computer Vision VII, (27 March 1989); doi: 10.1117/12.960298; https://doi.org/10.1117/12.960298