Statements like "X is can be used to represent any program/function, therefore it is all we are every going to need" are pretty silly.
Show this thread
-
Second, it is not relevant whether a program *can be represented* (that's almost always true), one care whether a program *can be developed* (not just in theory, but in practice) using a particular approach.
Show this thread
So statements like "NNs are universal approximators (or, 'there are Turing-complete RNN architectures'), therefore DL has no limits" is like saying "you can use a pen & some paper to produce the complete works of Shakespeare". Technically true, but pretty silly at the same time.
-
-
deconstructing the hype
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Darn it. So perhaps I should step away from using IBM System/360 assembly language to build an AGI?
-
give IBM z/Series assembler a try. come on in, the water's warm and Grande.
End of conversation
New conversation -
-
-
Couldn't agree less
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Take a real problem(early diagnosis of pancreas cancer) and come up with a better solution using only NN. No? What are we doing then?
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.