Not all functions we want to learn can be built efficiently from differentiable parts. What's less obvious to me right now: could all the important metalearning functions turn out to be differentiable? (not that they have to!)
-
-
Is there an intuitive way to categorize this class of functions? I guess anything that has a lot of abstract structure and interdependencies.
-
Loops and recurrences seem to be major issues.
- 4 more replies
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.