Teaching and Explanation: Aligning Priors between Machines and Humans

Machine intelligence differs signficantly from human intelligence. While human perception has similarities to the way machine perception works, human learning is mostly a directed process, guided by other people: parents, teachers, ... The area of machine teaching is becoming increasingly popular as a different paradigm for making machines learn. In this chapter, we start from recent results in machine teaching that show the relevance of prior alignment between humans and machines. From here, we focus on the scenario when a machine has to teach humans, a situation more and more common in the future. Specifically, we analyse how machine teaching relates to explainable artificial intelligence, and how simplicity priors play a role beyond intelligibility. We illustrate this with a general teaching protocol and a few examples in several representation languages: feature-value vectors and sequences. Some straightforward experiments with humans indicate when a strong simplicity prior is --and is not-- sufficient.