When searching for truth, it is wrong to cut off areas of the search space before you prove that they must be empty, which requires a metatheory of the space you are searching. But once you have that metatheory, it is also wrong to not discard areas that you know to be empty.
-
-
I am arguing that there is no global optima. We just have a bunch of local optima that just keeps moving with time me. It's a distributed system, so to speak
-
What makes you so sure? If you try to model a function, would a proof that there is no global optimum in model space (i.e. one function that models that function best) not surprise you?
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.