This touches on some of the reasons I suspect deep learning is much less impressive than currently believed:https://twitter.com/maradydd/status/698660117902807042 …
@ctbeiser Because the type of mistake is one people would never make. Understanding why the net *does* make that type of mistake will (IMO)>
-
-
@Meaningness But if machines won't make the mistake of thinking photoshopped images are real, does that mean humans aren't that impressive? -
@Meaningness The model is obviously different. That both can make mistakes when you craft for that seems entirely unremarkable. - 2 more replies
New conversation -
-
-
@ctbeiser > lead to understanding what it is actually doing—which is not what its creators think. (I think!)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.