Learning reversible symplectic dynamics

04/26/2022

∙

Time-reversal symmetry arises naturally as a structural property in many dynamical systems of interest. While the importance of hard-wiring symmetry is increasingly recognized in machine learning, to date this has eluded time-reversibility. In this paper we propose a new neural network architecture for learning time-reversible dynamical systems from data. We focus in particular on an adaptation to symplectic systems, because of their importance in physics-informed learning.

READ FULL TEXT

Learning reversible symplectic dynamics

Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data

Dimensionless machine learning: Imposing exact units equivariance

Physics-Informed Convolutional Neural Networks for Corruption Removal on Dynamical Systems

Robust physics discovery via supervised and unsupervised pattern recognition using the Euler characteristic

Structural Equivalences for Reversible Calculi of Communicating Systems (Oral communication)

Feynman Machine: The Universal Dynamical Systems Computer

Phase2vec: Dynamical systems embedding with a physics-informed convolutional network

Learning reversible symplectic dynamics

Related Research

Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data

Dimensionless machine learning: Imposing exact units equivariance

Physics-Informed Convolutional Neural Networks for Corruption Removal on Dynamical Systems

Robust physics discovery via supervised and unsupervised pattern recognition using the Euler characteristic

Structural Equivalences for Reversible Calculi of Communicating Systems (Oral communication)

Feynman Machine: The Universal Dynamical Systems Computer

Phase2vec: Dynamical systems embedding with a physics-informed convolutional network