@fchollet yet. Nice challenge.
Deep learning is actually pretty boring, except for this one thing: it works. It's the real deal. Too bad it doesn't explain anything...
-
-
- End of conversation
New conversation -
-
-
@fchollet (I really wish I understood why deep nets regularize so much better than they have any right to.) -
@michael_nielsen@fchollet they don't? It's just that optimization sucks: finding the global optimum that overfits the train set is hard ;-) - Show replies
New conversation -
-
-
@fchollet Have you tried training the network on supervised datasets of several million good and bad explanations?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
so there is nothing much to say about something with a cute name that nobody knows quite what it means except that it does something that nobody can quite define with precision and we really have no idea how to talk about it. Did I miss something?
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.