"bulk of human knowledge is
…causal, not probabilistic"
grammar of stats is insufficient
Judea Pearl
ht @Plinz
"Cognition…also just another way of doing stats"https://twitter.com/TTIVanguard/status/1006524568457170945 …
-
If a model gives better predictions than a statistical model, it is a better statistical model.
it would seem that you would encompass literally everything into your definition of statistics, which makes what you say true but trivial, no?
-
-
It took me a long time to see it that way, so to me it is not trivial (I used to see it the same way as yourself, I think). I might also change my view, but it would require to change my understanding of the nature of representation and function approximation, I suppose.
-
may be slightly worse…it's true & unhelpful… call it the Turing Trap ~futile universalization…Turing machine alone ≠ real problems solved…need problem-specific functions & algorithms
- 3 more replies
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.