Re:Natural language benchmarks don’t measure AI models’ gene...
by mjburgess on Monday August 24, 2020 @08:03AM
(#24259787)
I'm conflating them because they are deeply connected.
Causal analysis can be performed, via Pearl, on datasets collected for causal analysis.
You still need some mechanism to collect the data, ie., the scientist. This requires solving the "relevance" (/framing) problem -- which, in my view, cannot be solved under a congitivist (/computational) theory of mind.
"Data" which is relevant to a causal hypothesis isn't selected via inference, the body "selects" it.
eg., when my hand is on a hot surface, it's temperature isnt "chosen as the relevant casual variable".
The body is the primary solution to the relevance problem. So you can't just "shove in causal math" into a computational system and expect it to grasp anything.
I also don't think bootstrapping will take you very far: causal models of, eg., dogs are very deep. ie., we understand their 2d, 3d, skeletal, behavioural, color, sound etc. "dimensions".
To say, "the dog was well behaved" requires an extraordinarily deep model of "dog".
The only way i see this being built is via play, ie., via hypothetical interaction with an environment -- as we do -- with bodies capable of discerning relevance.
Causal analysis can be performed, via Pearl, on datasets collected for causal analysis.
You still need some mechanism to collect the data, ie., the scientist. This requires solving the "relevance" (/framing) problem -- which, in my view, cannot be solved under a congitivist (/computational) theory of mind.
"Data" which is relevant to a causal hypothesis isn't selected via inference, the body "selects" it.
eg., when my hand is on a hot surface, it's temperature isnt "chosen as the relevant casual variable".
The body is the primary solution to the relevance problem. So you can't just "shove in causal math" into a computational system and expect it to grasp anything.
I also don't think bootstrapping will take you very far: causal models of, eg., dogs are very deep. ie., we understand their 2d, 3d, skeletal, behavioural, color, sound etc. "dimensions".
To say, "the dog was well behaved" requires an extraordinarily deep model of "dog".
The only way i see this being built is via play, ie., via hypothetical interaction with an environment -- as we do -- with bodies capable of discerning relevance.