Abstract

AI systems are expected to impact the ways we communicate, learn, and interact with technology. However, there are still major concerns about their commonsense reasoning, and personalization. This article computationally explains causal (vs. statistical) inference, at different levels of abstraction, and provides three examples of how we can use do-operator, a mathematical operator for intervention, to address some of these concerns. The first example is from an educational module that I developed and implemented for undergraduate engineering students, as part of an educational research project with the US National Science Foundation. For the first time, to the best of my knowledge, 117 students could successfully use do-operator in a cybersecurity investment decision, according to Bloom’s learning taxonomy. Gender did not make a significant difference in the students’ performance, according to the Mann–Whitney U test. The second example explains using do-operator in assessing the effectiveness of intelligent tutoring systems, ITS, in receiving higher grades. The third example sheds light on combining online learning and offline learning, in reinforcement learning, to find the optimal policy that maximizes reward. To shed light on future research on explainability and personalization, I offer two recommendations: 1- Learn like System 2, the conscious learner (based on Bengio’s proposal for deep learning 2.0), and 2- Preference, a process, not an object (based on preference analysis of 25,646 registrants, entities and individuals purchasing domain names). In conclusion, this article contributes to achieving the goal of human–AI: Machines that think that learn and that create.