Rich Caruana will agree with this.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
you deserve the title: unrepentant hype buster.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I'm tense from being lied to.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Models are acyclic and one dimensional, while inputs contain many dimensions.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
s/tensors/GPUs/
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
pay-per-tensor?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Learning in a model depends on how the indivisual neurons are connected and not how many of them are connected with each other...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
True - Deep layers may not be actually needed in many applications...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet ... Compact models with smaller number of layers are easy to intrepret.. They no longer remain a black box .. what do you say??.. -
interpret*
- Show 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.