Experimentally Comparing Uncertain Inference Systems to Probability
This work addresses the selection of uncertain inference systems for applications by evaluating their robustness and biases, though it is incremental as it builds on existing systems without introducing new paradigms.
The paper compares the biases and performance of uncertain inference systems, including Mycin variants and a simplified probability method, finding that all three generally yield accurate results but the conditional independence assumptions provide the most robust outcomes, with some systems performing worse than random in specific cases.
This paper examines the biases and performance of several uncertain inference systems: Mycin, a variant of Mycin. and a simplified version of probability using conditional independence assumptions. We present axiomatic arguments for using Minimum Cross Entropy inference as the best way to do uncertain inference. For Mycin and its variant we found special situations where its performance was very good, but also situations where performance was worse than random guessing, or where data was interpreted as having the opposite of its true import We have found that all three of these systems usually gave accurate results, and that the conditional independence assumptions gave the most robust results. We illustrate how the Importance of biases may be quantitatively assessed and ranked. Considerations of robustness might be a critical factor is selecting UlS's for a given application.