Less a "problem" than a partial definition:https://www.technologyreview.com/s/604087/the-dark-secret-at-the-heart-of-ai …
-
-
There's no human comprehension of synthetic superintelligence by definition.
-
And what about deep learning networks?
-
Initial suspicion has to be that the distinction between "deep learning" and intelligence is not very robust.
-
Well it's not true that there's no human comprehension of deep learning networks. For eg, there's a fantastic summary of work done on feature visualisation at the new distil blog herehttps://distill.pub/2017/feature-visualization/ …
End of conversation
New conversation -
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.