Writing my deep learning book. I am pretty bad at writing, but hopefully I am better at mental images.pic.twitter.com/c5zJbknXZn
-
-
lovely way to put it. :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
what is the expected math level of your readers? [Any mental image of the linear algebra basics would be greatly appreciated.]
-
I've been following this video series https://twitter.com/3blue1brown/status/761371892418654208 … great visual explanations of linear algebra basics!
End of conversation
New conversation -
-
-
One thing I'm starting to realize is that all the secondary applications of nnets comes from the fact they're not perfect at this.
-
If you had a perfect uncrumpler, you wouldn't need hierarchical representations, intermediate activations, etc.
End of conversation
New conversation -
-
-
Nice! And feeds into the “Data has shape. Shape matters.” narrative of my own research field (Topological Data Analysis)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Almost like saying that Deep Learning is "Just Math". ;-) I agree though, the higher abstraction framework helps!
#deeplearningThanks. 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.