Re:The Modern Mathematics of Deep Learning
by joe_the_user on Saturday June 12, 2021 @07:17PM
(#27488260)
Well, I quote the statement to show how vague it is, among things.
Neural networks are "universal approximators" in that they work as well as virtually any previous approximation method. So given big snapshot of input data and human judgement on it, they can approximate that. They can also approximate a snapshot of some input-output pairs not produced by human but having patterns (solutions to differential equations, for example).
So, they can approximate what humans do in a given domain. But there's no reason to think they're acting in the same way as humans and I'd say very few people seriously working on ML believe that.
Neural networks are "universal approximators" in that they work as well as virtually any previous approximation method. So given big snapshot of input data and human judgement on it, they can approximate that. They can also approximate a snapshot of some input-output pairs not produced by human but having patterns (solutions to differential equations, for example).
So, they can approximate what humans do in a given domain. But there's no reason to think they're acting in the same way as humans and I'd say very few people seriously working on ML believe that.