Research
Science needs a way to process models that are only 'mostly correct' in terms of their predictions, but are very compressive (high ratio bet…
Science needs a way to process models that are only 'mostly correct' in terms of their predictions, but are very compressive (high ratio between predictive power and model complexity). They are likely
Science needs a way to process models that are only "mostly correct" in terms of their predictions, but are very compressive (high ratio between predictive power and model complexity). They are likely onto something.
Related
- Simplicity is a very strong signal of model quality. Galileo's heliocentric model was directionally correct, but its predictive power was qu…
- We should view the history of physics as a long-running program synthesis task. Kepler and Newton were searching the space of possible symbo…
- The reason symmetry is so important in physics is because symmetry is a highly effective compression operator. If a system is invariant unde…
- PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures
Source: Francois Chollet (X) | 2026-04-09