OK, I feel all this is wrong-headed, but I feel an obligation to share it with you anyway. This post summarizes a talk by Joshua Tenenbaum, who is focused on the question, ""How do we go beyond the idea of intelligence as recognizing patterns in data and approximating functions and more toward the idea of all the things the human mind does when you're modeling the world, explaining and understanding the things you're seeing." I think there's a big (and wrong) presumption that this is what the brain does. But many (probably most) people disagree with me, and would agree that "Our minds are built not just to see patterns in pixels and soundwaves but to understand the world through models." That's why they'd probably be comfortable with the idea of neuro-symbolic AI, or as Tenenbaum calls it, "the game engine in our head." Anyhow. Enjoy the paper.
Today: 4 Total: 106 [Direct link] [Share]
