Improving Simulations with Symmetry Control Neural Networks
This work addresses the challenge of simulating physical systems with conserved quantities, but it appears incremental as it builds upon existing Hamiltonian Neural Networks.
The paper tackled the problem of learning and exploiting symmetry constraints in physical system dynamics by proposing a method based on Hamiltonian Neural Networks, achieving improved accuracy on simple classical dynamics tasks.
The dynamics of physical systems is often constrained to lower dimensional sub-spaces due to the presence of conserved quantities. Here we propose a method to learn and exploit such symmetry constraints building upon Hamiltonian Neural Networks. By enforcing cyclic coordinates with appropriate loss functions, we find that we can achieve improved accuracy on simple classical dynamics tasks. By fitting analytic formulae to the latent variables in our network we recover that our networks are utilizing conserved quantities such as (angular) momentum.