The "Black Box" problem has historically been an concern when it comes to AI adoption. This article dives into the issue, and presents an interesting solution for letting AI itself explain its logic.
Can A.I. Be Taught to Explain Itself?
Can A.I. Be Taught to Explain Itself? Photo illustration by Derek Brahney. Source photo: J.R. Eyerman / The Life Picture Collection / Getty Images. In September, Michal Kosinski published a study that he feared might end his career. The Economist broke the news first, giving it a self-consciously anodyne title: "Advances in A.I.