Monitoring AI systems: A Problem Analysis, Framework and Outlook
This addresses the need for oversight in deployed AI systems, but it is incremental as it adapts existing monitoring approaches to a new context.
The paper tackles the problem of monitoring operational AI systems by proposing the use of knowledge-based systems, and it provides a framework to structure future research in this area.
Knowledge-based systems have been used to monitor machines and processes in the real world. In this paper we propose the use of knowledge-based systems to monitor other AI systems in operation. We motivate and provide a problem analysis of this novel setting and subsequently propose a framework that allows for structuring future research related to this setting. Several directions for further research are also discussed.