Hamiltonian Neural Network

Hamiltonian Neural Networks (HNNs) leverage the principles of Hamiltonian mechanics to improve the accuracy and efficiency of neural network models for dynamical systems. Current research focuses on enhancing HNN architectures, such as incorporating symplectic integrators for improved energy conservation and developing variations like dissipative HNNs to handle non-conservative systems, often employing Graph Neural Networks for complex systems. This approach offers significant advantages in areas like system identification, long-term prediction, and medical image analysis by incorporating physical constraints, leading to improved generalization and reduced data requirements.

Papers

January 19, 2023

Hamiltonian Neural Networks with Automatic Symmetry Detection
Eva Dierkes, Christian Offen, Sina Ober-Blöbaum, Kathrin Flaßkamp
Approximate Symmetry Hamiltonian Neural Network Hamiltonian System Symmetry Detection Symplectic Group

January 4, 2023

Machine Fault Classification using Hamiltonian Neural Networks
Jeremy Shen, Jawad Chowdhury, Sourav Banerjee, Gabriel Terejanu
Binary Classification Hamiltonian Neural Network Mechanical Engineering Energy Shaping Machinery Fault

September 23, 2022

Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network
Ravinder Bhattoo, Sayan Ranu, N. M. Anoop Krishnan
Rigid Body Hamiltonian Neural Network Hybrid System Lagrangian Neural Network Tensegrity Robot

September 22, 2022

Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems
Suresh Bishnoi, Ravinder Bhattoo, Sayan Ranu, N. M. Anoop Krishnan
Dynamical System Inductive Bias Graph Neural Hamiltonian Neural Network Lagrangian Neural Network Pseudo Hamiltonian

September 19, 2022

Physics-Informed Machine Learning of Dynamical Systems for Efficient Bayesian Inference
Somayajulu L. N. Dhulipala, Yifeng Che, Michael D. Shields
Dynamical System Bayesian Inference Physic Informed Machine Learning Hamiltonian Neural Network Inference Problem Efficient Bayesian Inference

August 22, 2022

Constants of motion network
Muhammad Firmansyah Kasim, Yi Heng Lim
Neural Network Motion Information Physical System Hamiltonian Neural Network Motion Estimation Network Mathematical Constant

August 12, 2022

Bayesian Inference with Latent Hamiltonian Neural Networks
Somayajulu L. N. Dhulipala, Yifeng Che, Michael D. Shields
Bayesian Inference Hamiltonian Monte Carlo Hamiltonian Neural Network

April 11, 2022

Learning Trajectories of Hamiltonian Systems with Neural Networks
Katsiaryna Haitsiukevich, Alexander Ilin
Neural Network Hamiltonian Neural Network Hamiltonian System Hidden Physic Continuous Time Trajectory

April 9, 2022

Neuronal diversity can improve machine learning for physics and beyond
Anshul Choudhary, Anil Radhakrishnan, John F. Lindner, Sudeshna Sinha, William L. Ditto
Neural Network Machine Learning Theoretical Physic Hamiltonian Neural Network Homogeneous Neural Network Conventional Neural Network Neuronal Diversity

February 28, 2022

Learning Neural Hamiltonian Dynamics: A Methodological Overview
Zhijie Chen, Mingquan Feng, Junchi Yan, Hongyuan Zha
Deep Learning Framework Hamiltonian Neural Network Hamiltonian System Hamiltonian Dynamic Methodological Insight

February 10, 2022

Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Nate Gruver, Marc Finzi, Samuel Stanton, Andrew Gordon Wilson
Inductive Bias Physic Based Model Hamiltonian Neural Network Lagrangian Neural Network Conservative System

January 25, 2022

Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately
Andrew Sosanya, Sam Greydanus
Hamiltonian Neural Network Local Non Dissipativity Conservative System Dissipative Dynamic Energy Dissipation Law

November 19, 2021

Physics-enhanced Neural Networks in the Small Data Regime
Jonas Eichelsdörfer, Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis
Physic Informed Neural Network Low Data Regime Hamiltonian Neural Network Lagrangian Neural Network Initial Condition

November 10, 2021

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision
Irina Higgins, Peter Wirnsberger, Andrew Jaegle, Aleksandar Botev
Vision Paper Quality Issue Latent Dynamic Hamiltonian Learning Hamiltonian Neural Network Hamiltonian Dynamic Phase Space Symplectic Group