causal
Neural Networks Lack Causality And Object Concepts
Humans possess basic foundational knowledge — intuitive physics, cause and effect, and the notion that the world is divided into persistent objects — that neural networks fundamentally lack and may not be able to learn from data, as shown when a Breakout-playing system that learned only from pixels failed completely when the paddle was moved up two pixels because it never abstracted the notion of a paddle as an object.
causalpending
Speaker
Melanie MitchellEvidence Quote
“it hadn't abstracted the notion of a paddle as an object. It's just a bunch of pixels. It was as if we would see the world and not see objects.”
Source
68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense— Sean Carroll's MindscapeCreated: 6/13/2026, 12:06:58 AM
Your notes
Loading notes...