Machine Coaching

This position paper puts forward machine coaching as a form of interactive machine learning that emphasizes the requirement for humans and machines to externalize their internal reasoning process in a manner that is understandable, at least at a basic level, by the other party. We posit that this mutual understanding leads to a computationally and cognitively lighter interaction, supports the run-time personalization of machines even by non-technically-savvy humans, makes any machine biases explicit and the process of their acquisition transparent, and facilitates the development of AI systems that can, by design, explain and be explained to. Backed by psychological theories of human reasoning and recent technical work, this paper adopts the working hypothesis that argumentation over symbolic rulebased knowledge offers a reasonable common language and semantics that machines and humans can utilize when interacting through machine coaching.