[thanatropism]

I'm used to random downvotes for comments about current controversies - I'll say things about income inequality that people won't like, and it's okay, you have your politics. Deep learning shouldn't be part of your politics, it either does stuff or doesn't.

Deep Learning is amazeballs for Computer Vision. It's fun because people like looking at pictures. But sufficiently prodded Isabelle proves theorems, I've seen it first hand, and the "sufficient prodding" is way underdeveloped yet. At one point backpropagation was dead too.