II-Learn—A Novel Metric for Measuring the Intelligence Increase and Evolution of Artificial Learning Systems

Abstract

A novel accurate and robust metric called II-Learn for measuring the increase of intelligence of a system after a learning process is proposed. We define evolving learning systems, as systems that are able to make at least one measurable evolutionary step by learning. To prove the effectiveness of the metric we performed a case study, using a learning system. The universality of II-Learn is based on the fact that it does not depend on the architecture of the studied system.

Keywords

• Machine learning
• Machine intelligence
• Intelligent system
• Evolving system
• Cooperative multiagent system
• Machine intelligence measure