Exactly, the ambition of ML often seems to be free lunch. And the No Free Lunch theorem says that will never happen.https://twitter.com/gewaltig/status/1193185916539621376 …
-
In other words, I agree with
@GaryMarcus. I just wanted to dampen peoples' enthusiasm for citing the No Free Lunch theorem in these arguments.
i correspondingly would like to dampen enthusiasm for thinking that real world problems have data distributed in IID format packaged neatly for current ML :)
-
-
Although I may repeat myself, not all ML techniques run after IID. (Statistical) relational learning is often considering a single mega example.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
IMO Goedel's incompleteness theorem kills AGI via machine learning. If you can solve a problem via optimization (implying completeness) then the problem is not sufficiently complex.
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.