Causal Independence for Knowledge Acquisition and Inference
This work addresses the challenge of building and using probabilistic models for knowledge engineers, though it is incremental as it builds on existing atemporal representations.
The paper tackles the problem of knowledge acquisition and inference in probabilistic models by introducing a temporal belief-network representation of causal independence, which simplifies inference and eliminates the need for unobservable variables, making it tractable for practical applications.
I introduce a temporal belief-network representation of causal independence that a knowledge engineer can use to elicit probabilistic models. Like the current, atemporal belief-network representation of causal independence, the new representation makes knowledge acquisition tractable. Unlike the atemproal representation, however, the temporal representation can simplify inference, and does not require the use of unobservable variables. The representation is less general than is the atemporal representation, but appears to be useful for many practical applications.