Re:The truth about deep learning
by argonaut on Thursday June 02, 2016 @04:55AM
(#11821171)
You missed my point entirely. My point is that showing something is a universal function approximator indicates nothing about whether that method is a good method in general. Necessary but not sufficient. kNN is one of the dumbest/simplest methods out there.
[ Parent
| on HN ]
a good method for what?