Quantifying and Simulating the Behavior of Knowledge-Based Interpretation Systems

V. R. Lesser, S. Reed, J. Pavlin

The beginnings of a methodology for quantifying the performance of knowledge-sources (KSs) and schedulers in a knowledge-based interpretation system are presented. As part of this methodology, measures for the "reliability" of an intermediate state of system processing and the effectiveness of KSs and schedulers are developed. Based on the measures, techniques for simulating KSs and schedulers of arbitrary effectiveness are described.

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.