What can the brain teach us about building artificial intelligence?
It addresses the problem of making AI more human-like for researchers in AI and cognitive science, but is incremental as it builds on existing work.
This paper provides a commentary on Lake et al.'s critique of AI achievements from the perspective of human intelligence, offering complementary suggestions for developing more human-like AI.
This paper is the preprint of an invited commentary on Lake et al's Behavioral and Brain Sciences article titled "Building machines that learn and think like people". Lake et al's paper offers a timely critique on the recent accomplishments in artificial intelligence from the vantage point of human intelligence, and provides insightful suggestions about research directions for building more human-like intelligence. Since we agree with most of the points raised in that paper, we will offer a few points that are complementary.