"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
-
Show this thread
-
Replying to @fchollet
LeCun is promoting “differentiable computing” as a new monicker to replace DL and NN. I like it
3 replies 12 retweets 93 likes -
Replying to @xtan
"Differentiable programming" is a lot better, but to be honest that seems a lot more general than what we do in deep learning. Deep learning is a very very small subset of what differentiable programming could be
3 replies 36 retweets 169 likes -
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.
2 replies 5 retweets 49 likes
Call it "Smooth" & introduce a new buzzword.
9:56 AM - 14 Jan 2018
0 replies
0 retweets
0 likes
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.