GEB is 1000 pages of this
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
People who talk about the inscrutability of neural networks are often complaining about the lack of mathematical proofs for optimality, convergence etc. If you bring them, it doesn't mean they will suddenly become scrutable :) any more than to 0.00000001% of mathematicians..
-
So to give a counter example would be an algorithm well-analyzed in the classical computation theory, like sorting.
End of conversation
New conversation -
-
-
generalized linear models are not self-explanatory but are highly scrutable
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Incel behavior qualifies
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Decision trees, linear models are easily interpretable. This gives a breakdown for different algorithms https://pbs.twimg.com/media/DTuzYroVAAAa1Rs.jpg:large …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Decision trees
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.