Can we really have both predictive accuracy AND interpretability? I don't know enough ML to evaluate this; thoughts? http://www.kdd.org/kdd2016/papers/files/rfp0573-ribeiroA.pdf …
A little like post hoc explanation in humans. Maybe I'm misunderstanding, though.
-
-
Ah! I am (somewhat) misunderstanding. Because the overall model is fixed in advance, not as bad as completely post hoc expn.
-
Still seems sus.
End of conversation
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.