Rule Learning
Cross-source consensus on Rule Learning from 1 sources and 6 claims.
1 sources · 6 claims
How it works
Comparisons
Evidence quality
Other
Highlighted claims
- τrule is defined as the first step where sample-level rule accuracy reliably exceeds 0.9. — The two clocks and the innovation window: When and how generative models learn rules
- Rule learning is controlled mainly by rule complexity. — The two clocks and the innovation window: When and how generative models learn rules
- Increasing parity group size delayed rule learning by roughly an order of magnitude for G=2 through G=4. — The two clocks and the innovation window: When and how generative models learn rules
- Rule learning corresponds to expansion of attractor basins for rule-valid vertices and shrinkage of rule-violating basins. — The two clocks and the innovation window: When and how generative models learn rules
- Dataset size has only mild effects on τrule in the parity experiments. — The two clocks and the innovation window: When and how generative models learn rules
- DSM loss separation for rule learning occurs mainly at intermediate noise scales. — The two clocks and the innovation window: When and how generative models learn rules