Feynman Dataset
A commonly used regression benchmark dataset in physics-informed machine learning, derived from the Feynman Lectures on Physics. It contains over 100 real physical formulas and is used to evaluate neural networks' ability to capture physical laws, particularly regarding parameter efficiency and generalization.
Timeline (last 90 days)
The researchers conducted computational experiments on two types of benchmarks: the Feynman dataset (physical formula regression tasks) and Gymnasium reinforcement learning benchmarks.
The Feynman dataset originates from the Feynman Lectures on Physics and contains more than 100 real physical formulas.
All Facts (2)
The researchers conducted computational experiments on two types of benchmarks: the Feynman dataset (physical formula regression tasks) and Gymnasium reinforcement learning benchmarks.
50%UnverifiedThe Feynman dataset originates from the Feynman Lectures on Physics and contains more than 100 real physical formulas.
50%