Causal Independence for Knowledge Acquisition and Inference

TL;DR

This paper presents a temporal belief-network model for causal independence that simplifies inference and knowledge acquisition without needing unobservable variables, making it practical for real-world applications.

Contribution

It introduces a new temporal belief-network representation of causal independence that improves inference efficiency and ease of knowledge elicitation over existing atemporal models.

Findings

Simplifies inference in causal models

Eliminates need for unobservable variables

Useful for practical applications

Abstract

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.