-
-
Replying to @sarahdoingthing @sjmoody
Learning on a *closed* set is trivial extension of optimization mental model. Learning in an open domain breaks it
1 reply 0 retweets 3 likes
ditto compute costs. For problems in P, you can throw compute cost into utility fn. For NP, you're screwed.
12:20 PM - 3 Dec 2016
0 replies
0 retweets
2 likes
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.