A Gauntlet for Evaluating Cognitive Architectures

Contents

We present a set of phenomena that can be used for evaluating cognitive architectures that aim at being designs for intelligent systems. To date, we know of few architectures that address more than a handful of these phenomena, and none that are able to explain all of them. Thus, these phenomena test the generality of a system and can be used to point out weaknesses in an architecture's design. The phenomena encourage autonomous learning, development of representations, and domain independence, which we argue are critical for a solution to the AI problem.