Posit: the problem of cognition has almost no overlap with supervised learning, what we're currently good at -- learning to map space x to space y given a dense sampling of x-cross-y
-
What about reinforcement learning? AlphaGo Zero definitely does not have a *dense* sampling of the space of boards to learn the board -> value mapping.
Definitely dense, since it runs on a convnet. By their very nature, convnets require to be exposed to a dense sampling of their data manifold. But that doesn't mean they need to be exposed to every possible input (e.g. every possible image, for an image classification model).
-
-
They are capable of generalization, but it is necessarily local generalization, i.e. pattern recognition.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I don't see why using a convnet should imply the need for a dense sampling of the input-output mapping. Do you have any links to papers where I could see it justified?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.