Sure, and this seems to sum up your argument. You seem to be saying: "if we don't solve these problems, we have a wall of unsolvable problems." But I don't see that wall; I only see many ideas to explore. And I don't see any suggestion that we lack ideas for productive variations
Right. But the issue is learning, not approximation (as discussed in Marcus 2001); if we don’t add means for learning operations over variables, the wall will come.https://twitter.com/dougblank/status/950381705852055552 …
-
-
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.