RADAR Test Methodology: Evaluating a Multi-Task Machine Learning System with Humans in the Loop

摘要

The RADAR (Reflective Agents with Distributed Adaptive Reasoning) project involves a collection of machine learning research thrusts that are integrated into a cognitive personal assistant. Progress is examined with a test developed to measure the impact of learning when used by a human user. Three conditions (conventional tools, Radar without learning, and Radar with learning) are evaluated in a large-scale, between-subjects study. This paper describes the RADAR Test with a focus on test design, test harness development, experiment execution, and analysis. Results for the 1.1 version of Radar illustrate the measurement and diagnostic capability of the test. General lessons on such efforts are also discussed.