World models should not rest on beliefs, but on understanding, where understanding means possession of a functional model that can reproduce the observables.
There is nothing special about past futures when learning. Your models have to explain the past as well.
-
-
No, just make sure that you don't include the known facts that you want to explain into the training set.
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.