factual

Causal Hierarchy Is A Theorem Limiting Machine Learning

It is not merely an opinion but a theorem—the causal hierarchy or ladder of causation—that you cannot move from level i to level i+1 without information or assumptions from level i+1 or higher, which mathematically constrains a robot's ability to perform certain tasks and proves pure data-driven deep learning cannot reach intervention or counterfactual reasoning.

factualpending

Speaker

Judea Pearl

Evidence Quote

“you cannot go from level I to level I plus one unless you have information or assumptions of level I plus one or higher.”

Source

196 | Judea Pearl on Cause and Effect— Sean Carroll's Mindscape
Created: 6/13/2026, 12:18:40 AM

Your notes

Loading notes...