What is your stance on @karpathy 's description of software 2.0?
If you want a more nuanced take on what deep learning can and cannot do, and why it definitely isn't a replacement for "programming" in any shape or form, check out this ML Street Talk episodehttps://www.youtube.com/watch?v=J0p_thJJnoo …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Neural networks not being turing complete doesn't mean they can't learn to use a turing complete medium
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thank you for your video (and Keras.) As an amateur trying to apply DL, I was surprised how dumb DL was: I needed thousands of data to teach the net something simple. But another idea is for algorithmic models to generate millions of data points for DL to train.
-
So a machine who knows they”truth of multiplication” can teach a dumb machine which only interpolates. Similar to how ABA teachers teach autistic children.
End of conversation
New conversation -
-
-
Wtf is gradient tape not on the damn GPU, inference is killing my machine! Gaad!
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.