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 Yes, the point is not that you can fool them, but that systematically figuring out *how* to fool them will reveal what they do.
-
-
@ctbeiser “It’s magic! They’re brains! We can’t understand them!” is much of the mystique of NNs. That needs to be broken.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
This Tweet is unavailable.
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.