Combining Symbolic Learning Techniques and Statistical Regression Analysis

Carlo Berzuini

This paper discusses relationships between statistical modeling techniques and symbolic learning from examples, and indicates types of learnine problem where a combined viewpoint may be very helpful. A novel computational approach is proposed which combines statistical modeling with a transformation procedure which maps the statistical model onto logical decision rules for the sake of domain experts’ intuitions. The proposed algorithm is illustrated by working through a simple but challenging case-study on learning prognostic rules from clinical observational data.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.