Proceedings of the Annual Conference of JSAI
Online ISSN : 2758-7347
38th (2024)
Session ID : 4Xin2-89
Conference information

Extracting Nonlinear Symmetries From Trained Neural Networks on Dynamics Data
*Yoh-ichi MOTOTAKE
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract

To support scientists developing reduced models of complex physics systems, we propose a method for extracting interpretable physical information from deep neural networks (DNNs) trained on time-series data of the physics system. Specifically, we propose a framework for estimating the hidden nonlinear symmetries of the system from DNNs trained on time-series data that can be regarded as a classical Hamiltonian dynamical system with finite degrees of freedom. The proposed framework is able to estimate the nonlinear symmetry corresponding to the Laplace--Lunge--Lenz vector, which is a conserved value that keeps the long axis direction of the elliptical motion of the planet constant, and visualize its Lie manifold.

Content from these authors
© 2024 The Japanese Society for Artificial Intelligence
Previous article Next article
feedback
Top