[R] Why Are We Using Black Box Models in AI When We Don't Need To? A Lesson From An Explainable AI Competition

The article isn't really insightful as it simply successfully attacks a very "weak" strawman. In particular, the article successfully challenges the assumption, quoting "that we must always sacrifice some interpretability to get the most accurate model" (emphasis on "always" mine) by choosing a particular problem on a tiny dataset where there exists a very, very simple model (a heuristic rule described in a single sentence) that gives acceptable accuracy. Yes, of course, there are many such problems, some "problem domains" are almost all like that and yes, for them there's no tradeoff involved. However, the article then tries to apply the same reasoning to a different class of problems (namely, the survey about robotic surgery and vision systems) without any reasonable grounds to do. They assume, quoting the penultimate sentence, "It is possible that an interpretable model can always be constructed--we just have not been trying."