"Neural networks" are a sad misnomer. They're neither neural nor even networks. They're chains of differentiable, parameterized geometric functions, trained with gradient descent (with gradients obtained via the chain rule). A small set of highschool-level ideas put together
-
-
I think that generality is intentional. "Differentiable programming" is a aspirational goal in which the building blocks used in deep learning have been modularized in a way that allows their flexible use in more general programming contexts.
-
NNs are one heuristic way of "solving" (well, approximating, no, not even that) a certain optimization problem. No need to (and actually misleading) to give this a name like XYZ programming, because it is very, very far from that generality.
- Show replies
New conversation -
-
-
What about “differential computing”? The functions involved are differentiable, not the computing; the computing part deals with differentials. Also, it sounds as a good companion for “differential calculus”.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
"Differential Programming" sounds a bit drab. I'm curious to know what you would call 'Neutral Networks'
@fcholletThanks. 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.