Re:Why not string theory? Because enough is enough
by tormeh on Sunday June 12, 2016 @12:12PM
(#11888744)
That's been solved by the most basic approach to ML: Supervised learning. A simplistic way to describe it would be that you say to the ML algorithm: "Here's two states, one at time N and one at time N+1. Your task is to predict the state at N+1 given the state at N. We have a bazillion of such state-pairs that you can test and refine your model on. Go nuts."
[ Parent
| on HN ]
Re:Why not string theory? Because enough is enough
by erikpukinskis on Sunday June 12, 2016 @01:21PM
(#11889142)
Supervised learning is what I'm talking about and it's not a solution to the frame problem. The human handler knows roughly the answers they looking for, and the machine learns details. The machine isn't discovering a new idea, it's just learning how to perform well inside a very small, well defined game that a human made.