Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data

by   Yaofeng Desmond Zhong, et al.

The last few years have witnessed an increased interest in incorporating physics-informed inductive bias in deep learning frameworks. In particular, a growing volume of literature has been exploring ways to enforce energy conservation while using neural networks for learning dynamics from observed time-series data. In this work, we present a comparative analysis of the energy-conserving neural networks - for example, deep Lagrangian network, Hamiltonian neural network, etc. - wherein the underlying physics is encoded in their computation graph. We focus on ten neural network models and explain the similarities and differences between the models. We compare their performance in 4 different physical systems. Our result highlights that using a high-dimensional coordinate system and then imposing restrictions via explicit constraints can lead to higher accuracy in the learned dynamics. We also point out the possibility of leveraging some of these energy-conserving models to design energy-based controllers.


A Differentiable Contact Model to Extend Lagrangian and Hamiltonian Neural Networks for Modeling Hybrid Dynamics

The incorporation of appropriate inductive bias plays a critical role in...

Learning Neural Hamiltonian Dynamics: A Methodological Overview

The past few years have witnessed an increased interest in learning Hami...

Physical Symmetries Embedded in Neural Networks

Neural networks are a central technique in machine learning. Recent year...

Time-Continuous Energy-Conservation Neural Network for Structural Dynamics Analysis

Fast and accurate structural dynamics analysis is important for structur...

Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control

In this paper, we introduce Symplectic ODE-Net (SymODEN), a deep learnin...

Lagrangian Neural Networks

Accurate models of the world are built upon notions of its underlying sy...

Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning

In this work, we introduce Dissipative SymODEN, a deep learning architec...