Hamiltonian Neural Networks from a Differential Geometry Perspective
The post explains Hamiltonian Neural Networks through differential geometry, showing why a normal MLP can fit motion data but still invent or lose energy over long rollouts. It shows that by learning a scalar Hamiltonian and deriving motion through the symplectic gradient, HNNs make energy conservation structurally unavoidable instead of hoping the network learns it from data.
https://abscondita.com/blog/symplectic-sledgehammer-for-a-spring
The post explains Hamiltonian Neural Networks through differential geometry, showing why a normal MLP can fit motion data but still invent or lose energy over long rollouts. It shows that by learning a scalar Hamiltonian and deriving motion through the symplectic gradient, HNNs make energy conservation structurally unavoidable instead of hoping the network learns it from data.
https://abscondita.com/blog/symplectic-sledgehammer-for-a-spring
Abscondita
Hamiltonian Neural Networks from a Differential Geometry Perspective
Because when given the simplest nail in the universe, sometimes you just need a nuclear powered sledgehammer.
Pure-Python symbolic regression that rediscovered Kepler's law from 8 data point
https://github.com/ariel95500-create/gp-elite
https://github.com/ariel95500-create/gp-elite
GitHub
GitHub - ariel95500-create/gp-elite: Régression symbolique par programmation génétique — lois interprétables en pur Python
Régression symbolique par programmation génétique — lois interprétables en pur Python - ariel95500-create/gp-elite