Improving Simulations with Symmetry Control Neural Networks

by   Marc Syvaeri, et al.

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.


page 1

page 2

page 3

page 4


Time-Reversal Symmetric ODE Network

Time-reversal symmetry, which requires that the dynamics of a system sho...

Learning a Gauge Symmetry with Neural Networks

We explore the capacity of neural networks to detect a symmetry with com...

Hamiltonian Neural Networks with Automatic Symmetry Detection

Recently, Hamiltonian neural networks (HNN) have been introduced to inco...

Noether: The More Things Change, the More Stay the Same

Symmetries have proven to be important ingredients in the analysis of ne...

Learning Hamiltonians of constrained mechanical systems

Recently, there has been an increasing interest in modelling and computa...

Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks

In this paper, we introduce interpretable Siamese Neural Networks (SNN) ...

Exploiting Different Symmetries for Trajectory Tracking Control with Application to Quadrotors

High performance trajectory tracking control of quadrotor vehicles is an...

Please sign up or login with your details

Forgot password? Click here to reset