One interesting thing about the ARC competition is that it serves to highlight how people who use deep learning often have little idea of what deep learning actually does, and when they should be using it or not
Show this thread
-
This is not about "following the rules" or breaking them, this is about understanding what you are doing. Being clueless is not the same as being creative.
Using deep learning as a universal & magical hammer you reach out to every time is actually the opposite of being creative
-
-
And the worst part is that people nowadays try the hammer first.
-
I would be hammering if I had the time
End of conversation
New conversation -
-
-
True, but VHS won.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Are you implying that adding more layers and compute doesn't solve every problem?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I agree...I will see papers where they achieved “State Of the Art” using DL on a dataset, but the results are only a tiny bit better. So it basically has roughly the same logic as random forest, but improved slightly through extensive parameter tuning.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I think we'll quickly learn that an intentional creative framework/process will become mandatory anyway... Not only for elegance, but for explainability [an ounce of prevention [creative foresight] is worth a pound of litigious crisis mitigation].
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.